Multi-Turn Language Model Reasoning

Follow this topic Ask about this topic

Latest papers

11 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Computation, Not Memory: Chain-of-Thought and State Tracking in LLM Agents
Oct 19, 2026Pedram Mouseli, Massieh MoayediCoT Reasoning Multi-Turn Language Model Reasoning
University of Toronto
SteerSearch: Interactive Search Reasoning with Mid-Response Steering
Oct 16, 2026Udit Thakur, Baohao Liao, Matteo Nulli +4Language Model Steering Retrieval-Augmented Reasoning
Language Technology Lab, University of Amsterdam · eBay
Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving
Oct 12, 2026Xin Cheng, Junming Yang, Ning XuMulti-Turn Language Model Reasoning LLM Reasoning
School of Computer Science and Engineering, Southeast University, Nanjing, China.
Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning
Aug 31, 2026Jie Liang, Zhengxin Yu, Hamid Nasiri +1Multi-Turn Language Model Reasoning Long-Horizon LLM Agents
School of Computing and Communications, Lancaster University, UK · School of Computing and Engineering, University of Huddersfield, UK
Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference
Aug 4, 2026Shahrukh Mohiuddin, Chalamalasetti Kranti, Sherzod Hakimov +1LLM Evaluation Multi-Turn Language Model Reasoning
Computational Linguistics, Department of Linguistics University of Potsdam, Germany · German Research Center for Artificial Intelligence (DFKI), Berlin, Germany
BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation
Jun 29, 2026Ankur Samanta, Akshayaa Magesh, Tal Lancewicki +7LLM Evaluation Multi-Turn Language Model Reasoning
Meta AI · Columbia University · Work done at Meta +2
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
Jun 9, 2026Sai Kartheek Reddy Kasu, Nils Lukas, Samuele PoppiCoT Faithfulness LLM Alignment
Independent Researcher · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
May 28, 2026Zizhuo Lin, Quanling Liu, Jinsheng Quan +6LLM Grounding Multi-Turn Language Model Reasoning
Zhejiang University · University of Science and Technology of China
Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents
Apr 6, 2026Neharika Jali, Anupam Nayak, Gauri JoshiMulti-Turn Language Model Reasoning Efficient Language Model Reasoning
Carnegie Mellon University
Adaptive Stopping for Multi-Turn LLM Reasoning
Apr 1, 2026Xiaofan Zhou, Huy Nguyen, Bo Yu +2Multi-Turn Language Model Reasoning Efficient Language Model Reasoning
Department of Computer Science, University of Illinois Chicago, Chicago, IL 60607, USA · Data science, Augustana College, Rock Island, IL 61201, USA · Department of Civil and Environmental Engineering, University of Utah, Salt Lake City, UT 84112, USA
Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction
Mar 5, 2026Xingwu Chen, Zhanqiu Zhang, Yiwen Guo +1Multi-Turn Language Model Reasoning RL for Language Model Reasoning
School of Computing and Data Science, The University of Hong Kong · LIGHTSPEED · Independent Researcher

Oct 19, 2026J/K move · Enter open · S save

Computation, Not Memory: Chain-of-Thought and State Tracking in LLM Agents

Pedram Mouseli, Massieh Moayedi

University of Toronto

CoT Reasoning Multi-Turn Language Model Reasoning Faithfulness of Language Model Reasoning

Open paper AskPDF arXiv

Language-model agents often reason before they act, and the value of monitoring that reasoning depends on how it relates to their actions. We ask how an agent's actions depend on its reasoning when the correct action depends on a changing state. In a small file-system task, background events announce which file's lock has been toggled but not its new value. The agent therefore has to reconstruct the current locks from its history before it can move files safely. With Qwen3-8B and Qwen3.5-9B, we separate two roles of reasoning: generating it before each action, and retaining earlier reasoning in the prompt. Most of the reduction in lock-violating commands comes from reasoning written at the moment of action. Retaining earlier reasoning adds little to rule-following, although it helps one model complete the task. The benefit depends on what the reasoning says. Filler text, reasoning written for another history and an accurate table of the state do not reproduce it. When we give the agent reasoning written for a history that differs in one lock value, the agent acts on that reasoning even against its own history. Without reasoning, linear probes recover the state from the model's activations about as well as a text classifier recovers it from the transcript. However, decoding accuracy does not predict which interventions change the agent's actions. In this setting, the benefit of reasoning for rule-following comes mainly from generating it at each step. The state that can be decoded without reasoning is a limited guide to how the agent acts.