Image de couverture de livre

Do Reasoning Models Ask Better Questions? A Formal Information-Theoretic Analysis on Multi-Turn LLM Games

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pedrozo, Daniel M., Soares, Telma W. de L., de Oliveira, Bryan L. M.
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
par: Deng, Yihe, et autres
Publié: (2023)

InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context
par: de Oliveira, Bryan L. M., et autres
Publié: (2025)

Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning
par: de Oliveira, Bryan L. M., et autres
Publié: (2024)

Is Data Shapley Not Better than Random in Data Selection? Ask NASH
par: Tian, Xiao, et autres
Publié: (2026)

Generative Data Refinement: Just Ask for Better Data
par: Jiang, Minqi, et autres
Publié: (2025)

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
par: Zhou, Zhanke, et autres
Publié: (2025)

Do Large Language Models Reason Causally Like Us? Even Better?
par: Dettki, Hanna M., et autres
Publié: (2025)

Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments
par: de Oliveira, Bryan L. M., et autres
Publié: (2025)

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design
par: Wei, Quan, et autres
Publié: (2025)

Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions
par: Zhang, Michael J. Q., et autres
Publié: (2024)

The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
par: Shin, Kwan Soo
Publié: (2026)

SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
par: Zhou, Yifei, et autres
Publié: (2025)

MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games
par: Eisenstein, Jacob, et autres
Publié: (2026)

When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification
par: Zhao, Jiale, et autres
Publié: (2026)

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
par: Liu, Bo, et autres
Publié: (2025)

Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game
par: Karabag, Mustafa O., et autres
Publié: (2025)

A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
par: Liu, Licheng, et autres
Publié: (2025)

Information-Theoretic Requirements for Gradient-Based Task Affinity Estimation in Multi-Task Learning
par: Zhang, Jasper, et autres
Publié: (2026)

Large Language Models Should Ask Clarifying Questions to Increase Confidence in Generated Code
par: Wu, Jie JW
Publié: (2023)

Partial Reasoning in Language Models: Search and Refinement Guided by Uncertainty
par: da Luz, Murilo, et autres
Publié: (2026)

Ask a Strong LLM Judge when Your Reward Model is Uncertain
par: Xu, Zhenghao, et autres
Publié: (2025)

DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification
par: Dipta, Shubhashis Roy, et autres
Publié: (2026)

Better LLM Reasoning via Dual-Play
par: Zhang, Zhengxin, et autres
Publié: (2025)

Multi-Turn Multi-Modal Question Clarification for Enhanced Conversational Understanding
par: Ramezan, Kimia, et autres
Publié: (2025)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
par: Didolkar, Aniket, et autres
Publié: (2025)

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning
par: Jali, Neharika, et autres
Publié: (2026)

CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures
par: Pandey, Punya Syon, et autres
Publié: (2025)

Better To Ask in English? Evaluating Factual Accuracy of Multilingual LLMs in English and Low-Resource Languages
par: Rohera, Pritika, et autres
Publié: (2025)

Formal Analysis of AGI Decision-Theoretic Models and the Confrontation Question
par: Saklakov, Denis
Publié: (2026)

Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
par: Ding, Yifeng, et autres
Publié: (2025)

Automating Deception: Scalable Multi-Turn LLM Jailbreaks
par: Kumarappan, Adarsh, et autres
Publié: (2025)

Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models
par: Yan, Xue, et autres
Publié: (2023)

MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters
par: Moore, H., et autres
Publié: (2026)

To Ask or Not to Ask: Learning to Require Human Feedback
par: Pugnana, Andrea, et autres
Publié: (2025)

Why Do More Experts Fail? A Theoretical Analysis of Model Merging
par: Wang, Zijing, et autres
Publié: (2025)

Evolving and Detecting Multi-Turn Deception using Geometric Signatures
par: Kumar, Surender Suresh, et autres
Publié: (2026)

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
par: Sareen, Kusha, et autres
Publié: (2025)

CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph Reasoning
par: Yang, Zukang, et autres
Publié: (2024)

Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing
par: Yang, Ning, et autres
Publié: (2026)

Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems
par: Mumcu, Furkan, et autres
Publié: (2026)