{ "reproducibility": { "generated_at_utc": "20260819T173809Z", "dataset": "milo_benchmark v1.0", "simulator": "Simulator (real AI2-THOR/Unity, restarted between episodes)", "planners": [ "rule_based", "behavior_tree", "htn", "react" ], "react_llm_provider": "qwen", "react_llm_model": "qwen2.5:7b", "memory_enabled": false, "note": "Merged from two real runs for the Space's leaderboard: rule_based/behavior_tree/htn from one co-run (experiments/results/milo_benchmark_htn_20260819T135510Z.json), react from a same-day reconfirm run (backend/planning_evaluation/results/react_v10_reconfirm_20260819T141303Z.json). Every number is a real, unmodified episode result; only the assembly into one file is synthetic." }, "summary_by_planner": { "rule_based": { "overall": { "n": 25, "goal_success_rate": 0.96, "execution_success_rate": 0.96 }, "by_tier": { "tier1_locate": { "n": 10, "goal_success_rate": 1.0, "execution_success_rate": 1.0 }, "tier2_pickup": { "n": 10, "goal_success_rate": 1.0, "execution_success_rate": 1.0 }, "tier3_store": { "n": 5, "goal_success_rate": 0.8, "execution_success_rate": 0.8 } }, "tier1_locate_grounded_check": { "n_tier1_tasks": 10, "n_perception_measured": 10, "exists_in_scene_ok": 10, "perceived_by_agent_ok": 9, "diverged_count": 1, "diverged_task_ids": [ "milo-v1-fp1-t1b" ], "perception_errors": [] } }, "behavior_tree": { "overall": { "n": 25, "goal_success_rate": 0.96, "execution_success_rate": 0.96 }, "by_tier": { "tier1_locate": { "n": 10, "goal_success_rate": 1.0, "execution_success_rate": 1.0 }, "tier2_pickup": { "n": 10, "goal_success_rate": 1.0, "execution_success_rate": 1.0 }, "tier3_store": { "n": 5, "goal_success_rate": 0.8, "execution_success_rate": 0.8 } }, "tier1_locate_grounded_check": { "n_tier1_tasks": 10, "n_perception_measured": 10, "exists_in_scene_ok": 10, "perceived_by_agent_ok": 9, "diverged_count": 1, "diverged_task_ids": [ "milo-v1-fp1-t1b" ], "perception_errors": [] } }, "react": { "overall": { "n": 25, "goal_success_rate": 0.8, "execution_success_rate": 0.8 }, "by_tier": { "tier1_locate": { "n": 10, "goal_success_rate": 1.0, "execution_success_rate": 1.0 }, "tier2_pickup": { "n": 10, "goal_success_rate": 1.0, "execution_success_rate": 1.0 }, "tier3_store": { "n": 5, "goal_success_rate": 0.0, "execution_success_rate": 0.0 } }, "tier1_locate_grounded_check": { "n_tier1_tasks": 10, "n_perception_measured": 10, "exists_in_scene_ok": 10, "perceived_by_agent_ok": 6, "diverged_count": 4, "diverged_task_ids": [ "milo-v1-fp1-t1a", "milo-v1-fp1-t1b", "milo-v1-fp201-t1b", "milo-v1-fp301-t1a" ], "perception_errors": [] } }, "htn": { "overall": { "n": 25, "goal_success_rate": 0.96, "execution_success_rate": 0.96 }, "by_tier": { "tier1_locate": { "n": 10, "goal_success_rate": 1.0, "execution_success_rate": 1.0 }, "tier2_pickup": { "n": 10, "goal_success_rate": 1.0, "execution_success_rate": 1.0 }, "tier3_store": { "n": 5, "goal_success_rate": 0.8, "execution_success_rate": 0.8 } }, "tier1_locate_grounded_check": { "n_tier1_tasks": 10, "n_perception_measured": 10, "exists_in_scene_ok": 10, "perceived_by_agent_ok": 9, "diverged_count": 1, "diverged_task_ids": [ "milo-v1-fp1-t1b" ], "perception_errors": [] } } }, "episodes": [ { "planner": "rule_based", "task_id": "milo-v1-fp1-t1a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the mug.", "goal": "find", "object": "mug", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 132.52167999962694, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp1-t1b", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the tomato.", "goal": "find", "object": "tomato", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 168.97172500011948, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": false, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp1-t2a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the apple.", "goal": "pick_up", "object": "apple", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 219.14074400046957, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp1-t2b", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the spoon.", "goal": "pick_up", "object": "spoon", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 145.74152600016532, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp1-t3a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier3_store", "instruction": "Put the bread away in the fridge.", "goal": "store", "object": "bread", "target": "fridge", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 745.4245300004914, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp5-t1a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the bowl.", "goal": "find", "object": "bowl", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 160.0087960005112, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp5-t1b", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the kettle.", "goal": "find", "object": "kettle", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 86.11799099980999, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp5-t2a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the potato.", "goal": "pick_up", "object": "potato", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 168.4694629993828, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp5-t2b", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the pan.", "goal": "pick_up", "object": "pan", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 150.68101300039416, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp5-t3a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier3_store", "instruction": "Put the mug away in the cabinet.", "goal": "store", "object": "mug", "target": "cabinet", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 658.0349169998954, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp201-t1a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier1_locate", "instruction": "Find the laptop.", "goal": "find", "object": "laptop", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 218.12064599998848, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp201-t1b", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier1_locate", "instruction": "Find the vase.", "goal": "find", "object": "vase", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 159.98114099966187, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp201-t2a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the newspaper.", "goal": "pick_up", "object": "newspaper", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 261.98743100030697, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp201-t2b", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the pillow.", "goal": "pick_up", "object": "pillow", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 343.2562460002373, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp201-t3a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier3_store", "instruction": "Put the remote control away in the drawer.", "goal": "store", "object": "remotecontrol", "target": "drawer", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 821.1723989998063, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp301-t1a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier1_locate", "instruction": "Find the alarm clock.", "goal": "find", "object": "alarmclock", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 2873.2748349993926, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp301-t1b", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier1_locate", "instruction": "Find the cell phone.", "goal": "find", "object": "cellphone", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 2897.313798999676, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp301-t2a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the boots.", "goal": "pick_up", "object": "boots", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 145.54633900024783, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp301-t2b", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the CD.", "goal": "pick_up", "object": "cd", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 185.23365300006844, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp301-t3a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier3_store", "instruction": "Put the book away in the drawer.", "goal": "store", "object": "book", "target": "drawer", "plan_success": true, "execution_success": false, "goal_success": false, "action_count": 8, "plan_step_count": 8, "failure_cause": "No valid positions to place object found", "wall_clock_ms": 3476.1707779998687, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp401-t1a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier1_locate", "instruction": "Find the towel.", "goal": "find", "object": "towel", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 381.1357719996522, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp401-t1b", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier1_locate", "instruction": "Find the candle.", "goal": "find", "object": "candle", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 104.56159699970158, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp401-t2a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the soap bar.", "goal": "pick_up", "object": "soapbar", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 190.08411000049819, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp401-t2b", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the toilet paper.", "goal": "pick_up", "object": "toiletpaper", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 172.94608100019104, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "rule_based", "task_id": "milo-v1-fp401-t3a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier3_store", "instruction": "Put the spray bottle away on the shelf.", "goal": "store", "object": "spraybottle", "target": "shelf", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 6, "plan_step_count": 6, "failure_cause": null, "wall_clock_ms": 638.6091250005848, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp1-t1a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the mug.", "goal": "find", "object": "mug", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 142.34934799969778, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp1-t1b", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the tomato.", "goal": "find", "object": "tomato", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 170.60117300025013, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": false, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp1-t2a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the apple.", "goal": "pick_up", "object": "apple", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 223.91353599959984, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp1-t2b", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the spoon.", "goal": "pick_up", "object": "spoon", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 175.56876999969973, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp1-t3a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier3_store", "instruction": "Put the bread away in the fridge.", "goal": "store", "object": "bread", "target": "fridge", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 822.1549820000291, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp5-t1a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the bowl.", "goal": "find", "object": "bowl", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 154.11710199987283, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp5-t1b", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the kettle.", "goal": "find", "object": "kettle", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 86.10937699995702, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp5-t2a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the potato.", "goal": "pick_up", "object": "potato", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 167.6921059997767, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp5-t2b", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the pan.", "goal": "pick_up", "object": "pan", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 156.69555800013768, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp5-t3a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier3_store", "instruction": "Put the mug away in the cabinet.", "goal": "store", "object": "mug", "target": "cabinet", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 669.150754999464, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp201-t1a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier1_locate", "instruction": "Find the laptop.", "goal": "find", "object": "laptop", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 200.05175799997232, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp201-t1b", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier1_locate", "instruction": "Find the vase.", "goal": "find", "object": "vase", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 166.50447499978327, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp201-t2a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the newspaper.", "goal": "pick_up", "object": "newspaper", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 258.44466499984264, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp201-t2b", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the pillow.", "goal": "pick_up", "object": "pillow", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 352.06007399938244, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp201-t3a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier3_store", "instruction": "Put the remote control away in the drawer.", "goal": "store", "object": "remotecontrol", "target": "drawer", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 870.348937000017, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp301-t1a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier1_locate", "instruction": "Find the alarm clock.", "goal": "find", "object": "alarmclock", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 2917.138148000049, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp301-t1b", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier1_locate", "instruction": "Find the cell phone.", "goal": "find", "object": "cellphone", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 2947.946197999954, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp301-t2a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the boots.", "goal": "pick_up", "object": "boots", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 149.96633600003406, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp301-t2b", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the CD.", "goal": "pick_up", "object": "cd", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 190.07257200064487, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp301-t3a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier3_store", "instruction": "Put the book away in the drawer.", "goal": "store", "object": "book", "target": "drawer", "plan_success": true, "execution_success": false, "goal_success": false, "action_count": 8, "plan_step_count": 8, "failure_cause": "No valid positions to place object found", "wall_clock_ms": 3421.1347770005887, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp401-t1a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier1_locate", "instruction": "Find the towel.", "goal": "find", "object": "towel", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 396.3659490000282, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp401-t1b", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier1_locate", "instruction": "Find the candle.", "goal": "find", "object": "candle", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 104.77389799962111, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp401-t2a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the soap bar.", "goal": "pick_up", "object": "soapbar", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 215.87691900003847, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp401-t2b", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the toilet paper.", "goal": "pick_up", "object": "toiletpaper", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 189.57333600064885, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "behavior_tree", "task_id": "milo-v1-fp401-t3a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier3_store", "instruction": "Put the spray bottle away on the shelf.", "goal": "store", "object": "spraybottle", "target": "shelf", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 6, "plan_step_count": 6, "failure_cause": null, "wall_clock_ms": 664.0696260001278, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp1-t1a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the mug.", "goal": "find", "object": "mug", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 148.80530400023417, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp1-t1b", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the tomato.", "goal": "find", "object": "tomato", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 170.04370099948574, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": false, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp1-t2a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the apple.", "goal": "pick_up", "object": "apple", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 278.2587349993264, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp1-t2b", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the spoon.", "goal": "pick_up", "object": "spoon", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 149.74088599956303, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp1-t3a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier3_store", "instruction": "Put the bread away in the fridge.", "goal": "store", "object": "bread", "target": "fridge", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 808.1917760000579, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp5-t1a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the bowl.", "goal": "find", "object": "bowl", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 149.92470099969069, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp5-t1b", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the kettle.", "goal": "find", "object": "kettle", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 93.68389900009788, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp5-t2a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the potato.", "goal": "pick_up", "object": "potato", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 177.29479999979958, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp5-t2b", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the pan.", "goal": "pick_up", "object": "pan", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 161.69941399948584, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp5-t3a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier3_store", "instruction": "Put the mug away in the cabinet.", "goal": "store", "object": "mug", "target": "cabinet", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 668.8048539999727, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp201-t1a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier1_locate", "instruction": "Find the laptop.", "goal": "find", "object": "laptop", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 204.33005899940326, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp201-t1b", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier1_locate", "instruction": "Find the vase.", "goal": "find", "object": "vase", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 170.00172400003066, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp201-t2a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the newspaper.", "goal": "pick_up", "object": "newspaper", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 272.90667799934454, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp201-t2b", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the pillow.", "goal": "pick_up", "object": "pillow", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 350.45225600060803, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp201-t3a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier3_store", "instruction": "Put the remote control away in the drawer.", "goal": "store", "object": "remotecontrol", "target": "drawer", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 8, "plan_step_count": 8, "failure_cause": null, "wall_clock_ms": 876.8618989997776, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp301-t1a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier1_locate", "instruction": "Find the alarm clock.", "goal": "find", "object": "alarmclock", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 2980.472266999641, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp301-t1b", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier1_locate", "instruction": "Find the cell phone.", "goal": "find", "object": "cellphone", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 3051.542285999858, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp301-t2a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the boots.", "goal": "pick_up", "object": "boots", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 156.4706910003224, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp301-t2b", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the CD.", "goal": "pick_up", "object": "cd", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 191.60024400025577, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp301-t3a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier3_store", "instruction": "Put the book away in the drawer.", "goal": "store", "object": "book", "target": "drawer", "plan_success": true, "execution_success": false, "goal_success": false, "action_count": 8, "plan_step_count": 8, "failure_cause": "No valid positions to place object found", "wall_clock_ms": 3543.7934279998444, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp401-t1a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier1_locate", "instruction": "Find the towel.", "goal": "find", "object": "towel", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 387.7760430004855, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp401-t1b", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier1_locate", "instruction": "Find the candle.", "goal": "find", "object": "candle", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 2, "plan_step_count": 2, "failure_cause": null, "wall_clock_ms": 106.81837999982235, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp401-t2a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the soap bar.", "goal": "pick_up", "object": "soapbar", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 198.95741899927089, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp401-t2b", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the toilet paper.", "goal": "pick_up", "object": "toiletpaper", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 181.6071049997845, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "htn", "task_id": "milo-v1-fp401-t3a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier3_store", "instruction": "Put the spray bottle away on the shelf.", "goal": "store", "object": "spraybottle", "target": "shelf", "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 6, "plan_step_count": 6, "failure_cause": null, "wall_clock_ms": 693.6673519994656, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 0, "llm_prompt_tokens": null, "llm_completion_tokens": null, "llm_token_usage_is_approximate": null }, { "planner": "react", "task_id": "milo-v1-fp1-t1a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the mug.", "goal": "find", "object": "mug", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 13430.44534500001, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": false, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp1-t1b", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the tomato.", "goal": "find", "object": "tomato", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 3371.3553189999175, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": false, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp1-t2a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the apple.", "goal": "pick_up", "object": "apple", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 6474.353801000007, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 841, "llm_completion_tokens": 124, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp1-t2b", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the spoon.", "goal": "pick_up", "object": "spoon", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 5548.666354000034, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 845, "llm_completion_tokens": 123, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp1-t3a", "scene": "FloorPlan1", "room_type": "kitchen", "difficulty_tier": "tier3_store", "instruction": "Put the bread away in the fridge.", "goal": "store", "object": "bread", "target": "fridge", "plan_success": false, "execution_success": false, "goal_success": false, "action_count": 0, "plan_step_count": 0, "failure_cause": "LLM produced malformed output after 3 attempt(s): Proposed action 'place' violates precondition(s): holding_target, container_ready.", "wall_clock_ms": 9746.627000999979, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 6, "llm_prompt_tokens": 1976, "llm_completion_tokens": 225, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp5-t1a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the bowl.", "goal": "find", "object": "bowl", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 1749.1443440000012, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp5-t1b", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier1_locate", "instruction": "Find the kettle.", "goal": "find", "object": "kettle", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 2592.6222319999397, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp5-t2a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the potato.", "goal": "pick_up", "object": "potato", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 6618.435681000051, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 848, "llm_completion_tokens": 121, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp5-t2b", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the pan.", "goal": "pick_up", "object": "pan", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 5650.197365000054, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 841, "llm_completion_tokens": 123, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp5-t3a", "scene": "FloorPlan5", "room_type": "kitchen", "difficulty_tier": "tier3_store", "instruction": "Put the mug away in the cabinet.", "goal": "store", "object": "mug", "target": "cabinet", "plan_success": false, "execution_success": false, "goal_success": false, "action_count": 0, "plan_step_count": 0, "failure_cause": "LLM produced malformed output after 3 attempt(s): Proposed action 'pickup' violates precondition(s): target_near.", "wall_clock_ms": 12035.933999999997, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 7, "llm_prompt_tokens": 2309, "llm_completion_tokens": 288, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp201-t1a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier1_locate", "instruction": "Find the laptop.", "goal": "find", "object": "laptop", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 1793.0295469999464, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp201-t1b", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier1_locate", "instruction": "Find the vase.", "goal": "find", "object": "vase", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 2668.1542369999534, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": false, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp201-t2a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the newspaper.", "goal": "pick_up", "object": "newspaper", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 6833.863668999925, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 852, "llm_completion_tokens": 121, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp201-t2b", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the pillow.", "goal": "pick_up", "object": "pillow", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 5567.736264000018, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 845, "llm_completion_tokens": 117, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp201-t3a", "scene": "FloorPlan201", "room_type": "living_room", "difficulty_tier": "tier3_store", "instruction": "Put the remote control away in the drawer.", "goal": "store", "object": "remotecontrol", "target": "drawer", "plan_success": false, "execution_success": false, "goal_success": false, "action_count": 0, "plan_step_count": 0, "failure_cause": "LLM produced malformed output after 3 attempt(s): Proposed action 'open' violates precondition(s): target_near.", "wall_clock_ms": 10538.290385999971, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 6, "llm_prompt_tokens": 1989, "llm_completion_tokens": 240, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp301-t1a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier1_locate", "instruction": "Find the alarm clock.", "goal": "find", "object": "alarmclock", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 1845.5667770000446, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": false, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 276, "llm_completion_tokens": 38, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp301-t1b", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier1_locate", "instruction": "Find the cell phone.", "goal": "find", "object": "cellphone", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 2308.0531059999885, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp301-t2a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the boots.", "goal": "pick_up", "object": "boots", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 6406.476108999982, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 848, "llm_completion_tokens": 118, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp301-t2b", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the CD.", "goal": "pick_up", "object": "cd", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 5267.015548000018, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 838, "llm_completion_tokens": 115, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp301-t3a", "scene": "FloorPlan301", "room_type": "bedroom", "difficulty_tier": "tier3_store", "instruction": "Put the book away in the drawer.", "goal": "store", "object": "book", "target": "drawer", "plan_success": false, "execution_success": false, "goal_success": false, "action_count": 0, "plan_step_count": 0, "failure_cause": "LLM produced malformed output after 3 attempt(s): Proposed action 'navigate' violates precondition(s): target_located.", "wall_clock_ms": 6223.6384939999425, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 4, "llm_prompt_tokens": 1292, "llm_completion_tokens": 145, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp401-t1a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier1_locate", "instruction": "Find the towel.", "goal": "find", "object": "towel", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 1839.6113559999776, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp401-t1b", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier1_locate", "instruction": "Find the candle.", "goal": "find", "object": "candle", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 1, "plan_step_count": 1, "failure_cause": null, "wall_clock_ms": 2399.09661899992, "llm_retry_attempts": 0, "goal_success_exists_in_scene": true, "goal_success_perceived_by_agent": true, "perception_error": null, "llm_call_count": 1, "llm_prompt_tokens": 275, "llm_completion_tokens": 37, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp401-t2a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the soap bar.", "goal": "pick_up", "object": "soapbar", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 6227.59505099998, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 851, "llm_completion_tokens": 122, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp401-t2b", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier2_pickup", "instruction": "Pick up the toilet paper.", "goal": "pick_up", "object": "toiletpaper", "target": null, "plan_success": true, "execution_success": true, "goal_success": true, "action_count": 3, "plan_step_count": 3, "failure_cause": null, "wall_clock_ms": 5887.970584999948, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 3, "llm_prompt_tokens": 865, "llm_completion_tokens": 130, "llm_token_usage_is_approximate": false }, { "planner": "react", "task_id": "milo-v1-fp401-t3a", "scene": "FloorPlan401", "room_type": "bathroom", "difficulty_tier": "tier3_store", "instruction": "Put the spray bottle away on the shelf.", "goal": "store", "object": "spraybottle", "target": "shelf", "plan_success": false, "execution_success": false, "goal_success": false, "action_count": 0, "plan_step_count": 0, "failure_cause": "LLM produced malformed output after 3 attempt(s): Action 'put_down' requires a target.", "wall_clock_ms": 10575.754352999978, "llm_retry_attempts": 0, "goal_success_exists_in_scene": null, "goal_success_perceived_by_agent": null, "perception_error": null, "llm_call_count": 6, "llm_prompt_tokens": 2045, "llm_completion_tokens": 248, "llm_token_usage_is_approximate": false } ], "totals": { "total_episodes": 100, "goal_succeeded": 92, "execution_succeeded": 92 } }