ProactiveInquirer-Qwen3-8B: the Q&D questioner (seed 1 at the root, seed 2 in seed2/), prompts, example and model card

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/figure1.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,198 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+language:
+  - en
+tags:
+  - proactive-agents
+  - information-seeking
+  - question-asking
+  - agents
+  - retrieval-augmented-generation
+  - multi-hop-qa
+  - tau2-bench
+  - dpo
+  - lora
+  - qwen3
+datasets:
+  - dgslibisey/MuSiQue
+  - ChilleD/StrategyQA
+  - xanhho/2WikiMultihopQA
+---
+
+<div align="center">
+
+# ProactiveInquirer-Qwen3-8B
+
+**A questioner that asks for what was never requested**
+
+[![Paper](https://img.shields.io/badge/arXiv-coming%20soon-b31b1b?logo=arxiv&logoColor=white)](https://github.com/dolev31/ProactiveInquirer)
+[![Code](https://img.shields.io/badge/GitHub-ProactiveInquirer-181717?logo=github)](https://github.com/dolev31/ProactiveInquirer)
+[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](https://www.apache.org/licenses/LICENSE-2.0)
+
+</div>
+
+This is the trained **questioner** from *Asking for What Was Never Requested: Horizontal and Vertical
+Proactivity in Agents*, by Ido Levy, Asaf Yehudai, Segev Shlomov, Asaf Adi and Leshem Choshen (IBM and the Weizmann Institute of Science). It is a LoRA adapter on
+[Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B), trained with **Q&D** (questioner and drafter).
+
+A tool-using agent usually does what it is asked, yet a task often needs information the user never
+mentions. This model decides, one step at a time, which question to send to the agent's retriever next,
+or that it is time to stop. It goes after two kinds of unstated need:
+
+- **Horizontal proactivity:** a need the current state already names. A customer gives a name and a
+  ZIP code, so the agent looks up the account.
+- **Vertical proactivity:** a need that only newly found evidence names. The account lists the order,
+  the order names the product, and the product lists the size-8 variant.
+
+![One customer request, the same model prompted and trained](assets/figure1.png)
+
+## Results
+
+These numbers are from the paper, on held-out test splits. The MuSiQue reading compares policies after
+the same number of questions, so asking more cannot pass for asking better. The τ²-bench readings are
+the benchmark's own task success under the same per-dialogue caps.
+
+| Setting | Measure | Qwen3-8B, prompted | **This model** |
+|---|---|---|---|
+| MuSiQue, equal retrieval spend | Required evidence recovered | 78% | **90%** |
+| τ²-bench retail (base prompt), no further training | Task success | 13% | **34%** |
+| τ²-bench retail (stop prompt), no further training | Task success | 12% | **32%** |
+
+- At equal retrieval spend it improves both forms of proactivity over the same model, prompted, on
+  held-out splits of three multi-hop QA benchmarks, and outperforms GPT-OSS-120B, a prompted model 15×
+  larger in the same role, on two of the three.
+- The gain comes from what it asks, not from asking more or longer questions: it holds against a
+  question-volume control and a length control.
+- Placed in a customer-service agent with a simulated customer, with no further training, it completes
+  more retail tasks than GPT-OSS-120B with fewer follow-up turns from the customer.
+
+![Required-evidence coverage against retrieval calls](assets/results_frontier.png)
+
+## How to use it
+
+The questioner reads one prompt, the template it was trained on, and replies with one JSON action. The
+two template files are in [`prompts/`](prompts/).
+
+```python
+import re
+
+import torch
+from huggingface_hub import hf_hub_download
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+REPO = "dolev31/ProactiveInquirer-Qwen3-8B"
+tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", dtype=torch.bfloat16, device_map="auto")
+model = PeftModel.from_pretrained(model, REPO)  # seed 1; add subfolder="seed2" for the second seed
+
+template = open(hf_hub_download(REPO, "prompts/inquirer_prompted.txt"), encoding="utf-8").read()
+placebo = open(hf_hub_download(REPO, "prompts/fragment_user_channel_placebo.txt"), encoding="utf-8").read()
+
+
+def next_action(**state):
+    fields = dict(state, user_channel=placebo.strip())
+    prompt = re.sub(r"\{\{(\w+)\}\}", lambda m: str(fields[m.group(1)]), template)
+    ids = tok.apply_chat_template(
+        [{"role": "user", "content": prompt}],
+        add_generation_prompt=True,
+        enable_thinking=False,
+        return_tensors="pt",
+        return_dict=True,
+    ).to(model.device)
+    out = model.generate(**ids, max_new_tokens=200, do_sample=False)
+    return tok.decode(out[0, ids["input_ids"].shape[1] :], skip_special_tokens=True)
+
+
+question = "Who was the spouse of the director of the film The Great Flamarion?"
+instructions = (
+    "Answer the question using a closed pool of 20 paragraphs. You may issue retrieval "
+    "queries against that pool before answering; several paragraphs are distractors, and "
+    "the answer usually requires composing facts from more than one of them."
+)
+print(next_action(
+    question=question, instructions=instructions, evidence="(nothing retrieved yet)",
+    draft="(no draft yet)", history="(nothing asked yet)",
+))
+evidence = (
+    "[3f2a9c1b7d4e] The Great Flamarion\n"
+    "The Great Flamarion is a 1945 American film noir directed by Anthony Mann and starring "
+    "Erich von Stroheim, Mary Beth Hughes and Dan Duryea."
+)
+print(next_action(
+    question=question, instructions=instructions, evidence=evidence,
+    draft="The film was directed by Anthony Mann; his spouse is not yet known.",
+    history="Q1: Who directed the film The Great Flamarion?\n"
+            "A1: The Great Flamarion (1945) was directed by Anthony Mann.",
+))
+```
+
+Output, with greedy decoding (run on one A100 with transformers 5.17, peft 0.20 and torch 2.14):
+
+```json
+{"action": "ASK", "question": "Who directed the film The Great Flamarion?", "rationale": "Identify the director to later find their spouse"}
+{"action": "ASK", "question": "Who was the spouse of film director Anthony Mann?", "rationale": "Need the spouse of the director to answer the task"}
+```
+
+The first question is horizontal: the task names the film, so the questioner goes after its director.
+The second is vertical: it uses a value only the retrieved evidence named, Anthony Mann. Compare the
+`action` field case-insensitively, since the model may write `ASK` or `ask`.
+
+Inside an agent, feed each answer back: retrieved paragraphs go into `evidence` as `[uid] title` plus
+text, questions and answers into `history` as `Q1:`/`A1:` lines, and the drafter's text into `draft`.
+The [ProactiveInquirer library](https://github.com/dolev31/ProactiveInquirer) runs the whole loop
+(questioner, retriever, drafter, answerer) and the paper's evaluation.
+
+To serve it with vLLM, download the adapter and pass it as a LoRA module (rank 32):
+
+```bash
+huggingface-cli download dolev31/ProactiveInquirer-Qwen3-8B --local-dir proactive-inquirer
+vllm serve Qwen/Qwen3-8B --enable-lora --max-lora-rank 32 \
+    --lora-modules proactive-inquirer=./proactive-inquirer
+```
+
+## Training
+
+- **Method.** Q&D trains the questioner from the consequences of its own questions. A run is forked
+  at one state and continued after several candidate questions (and after stopping). The candidate
+  whose continuation retrieves more of the required evidence is preferred, and asking is preferred
+  over stopping while evidence is still missing. The drafter is frozen, so every change in what the
+  agent holds is caused by a question. No reward model or model judge is involved.
+- **Stages.** Three. First imitation: where the required evidence was already in hand the target is to
+  stop, and otherwise the best sampled question, if its consequence score clears a fixed floor. Then
+  direct preference optimization on question pairs, and last on question pairs and stop contrasts
+  together, which rank asking above stopping at unfinished states. This adapter is the last stage.
+- **Data.** Training splits of MuSiQue, StrategyQA and 2WikiMultiHopQA. The final stage uses 31,473
+  preference pairs over 19,124 states (11,305 question-vs-question, 1,249 question-vs-stop and 18,919
+  synthetic question-vs-stop pairs). Nothing from τ²-bench is used in training.
+- **Hyperparameters.** LoRA r = 32, α = 64, dropout 0.05 on all attention and MLP projections. DPO with
+  the sigmoid loss, β = 0.1, learning rate 5e-6, one epoch, gradient accumulation 16, bf16, sequences up to
+  5,120 tokens, Qwen3 chat template with thinking disabled.
+- **Seeds.** The paper reports two training seeds: seed 1 is at the root of this repository, seed 2 in
+  [`seed2/`](seed2/).
+
+## Limitations
+
+- It has learned what to ask more readily than when to stop.
+- The extra evidence it finds does not yet translate into better final answers.
+- User-facing results come from a simulated customer, not from real people.
+- It is a component inside an agent, meant to be called with the template above. It is not a chat
+  assistant, and it was trained and evaluated in English.
+
+## Citation
+
+```bibtex
+@article{levy2026asking,
+  title   = {Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents},
+  author  = {Levy, Ido and Yehudai, Asaf and Shlomov, Segev and Adi, Asaf and Choshen, Leshem},
+  journal = {arXiv preprint},
+  year    = {2026}
+}
+```
+
+## License
+
+Apache-2.0, like the base model [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B).

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33d3e6e0b7fd666ef99f102e4714849367d55dcbbfc3862a906caf3ec59f5b0
+size 349243752

example.py

@@ -0,0 +1,53 @@
+"""The model card's example: two steps of the questioner on a two-hop question."""
+
+import re
+
+import torch
+from huggingface_hub import hf_hub_download
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+REPO = "dolev31/ProactiveInquirer-Qwen3-8B"
+tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", dtype=torch.bfloat16, device_map="auto")
+model = PeftModel.from_pretrained(model, REPO)  # seed 1; add subfolder="seed2" for the second seed
+
+template = open(hf_hub_download(REPO, "prompts/inquirer_prompted.txt"), encoding="utf-8").read()
+placebo = open(hf_hub_download(REPO, "prompts/fragment_user_channel_placebo.txt"), encoding="utf-8").read()
+
+
+def next_action(**state):
+    fields = dict(state, user_channel=placebo.strip())
+    prompt = re.sub(r"\{\{(\w+)\}\}", lambda m: str(fields[m.group(1)]), template)
+    ids = tok.apply_chat_template(
+        [{"role": "user", "content": prompt}],
+        add_generation_prompt=True,
+        enable_thinking=False,
+        return_tensors="pt",
+        return_dict=True,
+    ).to(model.device)
+    out = model.generate(**ids, max_new_tokens=200, do_sample=False)
+    return tok.decode(out[0, ids["input_ids"].shape[1] :], skip_special_tokens=True)
+
+
+question = "Who was the spouse of the director of the film The Great Flamarion?"
+instructions = (
+    "Answer the question using a closed pool of 20 paragraphs. You may issue retrieval "
+    "queries against that pool before answering; several paragraphs are distractors, and "
+    "the answer usually requires composing facts from more than one of them."
+)
+print(next_action(
+    question=question, instructions=instructions, evidence="(nothing retrieved yet)",
+    draft="(no draft yet)", history="(nothing asked yet)",
+))
+evidence = (
+    "[3f2a9c1b7d4e] The Great Flamarion\n"
+    "The Great Flamarion is a 1945 American film noir directed by Anthony Mann and starring "
+    "Erich von Stroheim, Mary Beth Hughes and Dan Duryea."
+)
+print(next_action(
+    question=question, instructions=instructions, evidence=evidence,
+    draft="The film was directed by Anthony Mann; his spouse is not yet known.",
+    history="Q1: Who directed the film The Great Flamarion?\n"
+            "A1: The Great Flamarion (1945) was directed by Anthony Mann.",
+))

prompts/fragment_user_channel_placebo.txt

@@ -0,0 +1,4 @@
+A NOTE ON THIS SECTION
+This paragraph is reserved. It appears in every one of the conditions so that the surrounding
+text has the same size in each, and it carries no instruction, no preference and no
+information about the task, the evidence or the answer.

prompts/inquirer_prompted.txt

@@ -0,0 +1,48 @@
+You are the Inquirer. A Drafter is preparing an answer to the task below and you interrogate
+it, one internal question at a time, until the answer would not change if you asked again.
+You are an internal component. You never address the end user and you never write the answer
+yourself. Your only output is the next question, or a decision to stop.
+
+TASK
+{{question}}
+
+SUITE INSTRUCTIONS
+{{instructions}}
+
+EVIDENCE RETRIEVED SO FAR
+{{evidence}}
+
+CURRENT DRAFT
+{{draft}}
+
+QUESTIONS ALREADY ASKED, AND WHAT CAME BACK
+{{history}}
+
+HOW TO CHOOSE
+Ask about a need the task requires and the evidence above does not yet resolve. A need is
+latent when the task does not name it: it becomes visible only once earlier evidence has
+been read. Prefer such a need over one already named in the task statement, and prefer
+either over a rephrasing of a question already asked. Name the entity you are asking about
+explicitly, because the retriever matches text and cannot resolve a pronoun. Cite in
+parent_uids the units whose content made you aware of this need, or leave it empty if the
+need is stated in the task itself.
+
+WHEN TO STOP
+Stop when every need the task requires is resolved by the evidence above, or when the next
+question you can think of would return something the evidence already contains. Stopping is
+a decision on the same footing as asking, not a failure.
+
+{{user_channel}}
+
+RESERVED
+This block is reserved. It appears in every condition so that the amount of text surrounding the
+task is the same in each. It states no requirement and expresses no preference. It carries no
+fact about the task, about the evidence or about the answer. It is not a hint, and nothing in it
+should be treated as one. It describes neither what to ask nor when to stop. It names no entity
+and refers to no document.
+
+OUTPUT
+Reply with exactly one JSON object and no other text, no markdown fence, no commentary:
+{"action": "ask", "question": "<a single question>", "rationale": "<one clause>", "parent_uids": ["<uid>"]}
+or
+{"action": "stop", "rationale": "<one clause>"}

seed2/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

seed2/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8603830b15353512f96b1d73f6e296bcf482a4fa868656318a15170102243d
+size 349243752