EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
Paper • 2607.02440 • Published • 33
Dipankar Sarkar PRO
dipankarsarkar
AI & ML interests
Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.
Recent Activity
upvoted a paper about 2 hours ago
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments upvoted a paper about 2 hours ago
Program-as-Weights: A Programming Paradigm for Fuzzy Functions upvoted a paper about 2 hours ago
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM AgentsOrganizations
upvoted 3
papers about 2 hours ago
upvoted 3
papers about 3 hours ago
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
Paper • 2607.00152 • Published • 3
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling
Paper • 2606.28661 • Published • 2
Building to the Test: Coding Agents Deliver What You Check, Not What You Requested
Paper • 2606.28430 • Published • 4
upvoted a paper about 17 hours ago
upvoted a paper about 19 hours ago
upvoted 2
papers about 20 hours ago
upvoted 2
papers about 21 hours ago
upvoted 2
papers about 22 hours ago
upvoted 4
papers about 23 hours ago
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
Paper • 2606.28322 • Published • 35
RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue
Paper • 2607.01213 • Published • 2
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
Paper • 2606.32017 • Published • 8
SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
Paper • 2606.30573 • Published • 4
upvoted 2
papers about 24 hours ago