LLM Reasoning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

68 papers in the last four weeks, up 143% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 650

All topics

Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents
May 30, 2026Yufeng WangAI Agent Reliability LLM Agent Evaluation
The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary
May 29, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuLLM Reasoning
The University of Hong Kong, Hong Kong, China · Brain Investing Limited, Hong Kong, China · Stellaris AI Limited, Hong Kong, China
Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
May 29, 2026Sanae Lotfi, Polina Kirichenko, Steven Li +1Overthinking in Language Models CoT Reasoning
1FAIR at Meta · 2Meta AI
What Am I Missing? Question-Answering as Hidden State Probing
May 29, 2026Chu Fei Luo, Samuel Dahan, Xiaodan ZhuLLM Self-Refinement Language Model Self-Assessment
Department of Electrical and Computer Engineering & Ingenuity Labs, Queen’s University · Conflict Analytics Lab, Queen’s University · Cornell Law School +1
LinTree: Improving LLM Reasoning with Explicitly Structured Search Histories
May 29, 2026Liwei Kang, Yee Whye Teh, Wee Sun LeeInference-Time Search Tree of Thoughts
National University of Singapore · University of Oxford
Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA
May 29, 2026Hao Chen, Xing Tang, Qirui Liu +6Retrieval-Augmented Generation Hallucination in Language Models
Shenzhen Technology University FiT, Tencent Shenzhen, China · South China University of Technology Guangzhou, China · The Hong Kong University of Science and Technology Hong Kong SAR, China +2
Reasoning with Sampling: Cutting at Decision Points
May 28, 2026Felix Zhou, Anay Mehrotra, Quanquan C. LiuMarkov Chain Monte Carlo Efficient Language Model Reasoning
Yale University · Stanford University
Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
May 28, 2026Zizhuo Lin, Quanling Liu, Jinsheng Quan +6LLM Grounding Reasoning Consistency in Language Models
Zhejiang University · University of Science and Technology of China
GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German
May 28, 2026Fabian Mewes, Anne Lauscher, Vagrant GautamGender Bias in Language Models Linguistic Bias in Language Models
JobMatchMe GmbH, Germany · Trustworthy AI Lab, University of Hamburg, Germany · Heidelberg Institute for Theoretical Studies, Germany
Conformal Certification of Reasoning Trace Prefixes
May 28, 2026Matt Y. Cheung, Ashok Veeraraghavan, Hanjie Chen +1Conformal Prediction Language Model Calibration
Department of Electrical & Computer Engineering, Rice University · Department of Computer Science, Rice University
ESPO: Early-Stopping Proximal Policy Optimization
May 28, 2026Zihang Li, Rui Zhou, Yingcheng Shi +8Early Stopping Reinforcement Learning
1Tongyi Lab , Alibaba Group · 2Peking University
Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies
May 28, 2026Yuxuan Ye, Raul Santos-Rodriguez, Edwin SimpsonLLM Grounding Claim Verification
Intelligent Systems Laboratory University of Bristol United Kingdom
TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation
May 28, 2026Yundong Kim, Heyoung YangLLM Evaluation Language Model Generation Evaluation
Applied Agent Research Center, Korea Institute of Science and Technology Information (KISTI), Republic of Korea · Department of Computer Science and Engineering, University of Seoul, Republic of Korea.
MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs
May 28, 2026Kevin Wang, Anna Thöni, Benjamin Kempinski +50LLM Agent Evaluation Strategic Reasoning Risks in Language Models
SURGENT: A Surgical Multi-Agent Assistance System Across the Perioperative Workflow
May 28, 2026Dongsheng Shi, Yue Li, Xin Yi +3Multi-Agent LLM Systems Clinical Decision Support
East China Normal University Shanghai, China · City University of Hong Kong Hong Kong SAR, China
Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
May 28, 2026Junlin He, Yihong Tang, Tong Nie +5LLM Pruning LLM Compression
The Hong Kong Polytechnic University, Hong Kong SAR, China · McGill University, Montreal, QC, Canada
Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective
May 28, 2026Shenghao Ye, Yuxiang Wang, Yu Guo +3Cost-Aware Inference LLM Uncertainty Estimation
University of Science and Technology of China · The University of Melbourne · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
May 28, 2026Chen He, Yuhao Wu, Lei Wang +2Fine-Tuning LLM Fine-Tuning
University of Electronic Science and Technology of China · Singapore University of Technology and Design · Singapore Management University
ReasonOps: Operator Segmentation for LLM Reasoning Traces
May 28, 2026Daniel Lee, Owen Queen, James ZouCoT Evaluation CoT Reasoning
Stanford University
CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models
May 27, 2026Venkat Akhil LakkapragadaSmall Language Models LLM Reasoning
Mistyoz AI Hyderabad, India
Skill-Conditioned Gated Self-Distillation for LLM Reasoning
May 27, 2026Jiazhen Huang, Xiao Chen, Xiao Luo +3Mathematical Reasoning Self-Distillation
Tsinghua University · University of Wisconsin-Madison · X-Humanoid +2
Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models
May 27, 2026Xinyuan Cheng, Beiduo Chen, Philipp Mondorf +1LLM Prompting LLM Reasoning
UMaiNLP, Center for Information and Language Processing, LMU Munich, Germany · ÆMunich Center for Machine Learning, Germany
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
May 27, 2026Linas Nasvytis, Simon Jerome Han, Ben Prystawski +3LLM Self-Refinement Efficient Language Model Reasoning
Stanford University
The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic
May 27, 2026Dominika Agnieszka Długosz, Arlindo Oliveira, Natalia Díaz-RodríguezLLM Evaluation Generalized Linear Models
Instituto Superior Técnico & INESC-ID, Universidade de Lisboa, Portugal · Dept. of Computer Science and AI & DaSCI Institute, Universidad de Granada, Spain
Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability
May 27, 2026Leizhen Zhang, Shuhan Chen, Sheng ChenLLM Evaluation Constraint Satisfaction
University of Louisiana at Lafayette, Lafayette, USA · East China Normal University, Shanghai, China
Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns
May 27, 2026Guni SharonInference-Time Search Tree of Thoughts
Texas A&M University
ProvMind: Provenance-grounded reasoning for materials synthesis
May 27, 2026Yiming Zhang, Ryo Tamura, Koji TsudaReasoning Evaluation Materials Science
Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan. · Center for Basic Research on Materials, National Institute for Materials Science, Tsukuba, Ibaraki, Japan. · RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.
Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning
May 27, 2026Yahan Yu, Noa Nakanishi, Fei ChengLLM Reasoning
Kyoto University, Japan
CIRF: Tokenizing Chain-of-Thoughts into Reusable Functional Units for Efficient Latent Reasoning in Large Language Models
May 27, 2026Yukyung Lee, Yumeng Shen, Jinhyeong Park +2CoT Reasoning Efficient Language Model Reasoning
Boston University · Hankuk University of Foreign Studies
Self-Consistency via Marginal Sharpening
May 27, 2026Aleksei Arzhantsev, Otmane Sakhi, Nicolas ChopinEfficient Language Model Reasoning Reasoning Consistency in Language Models
Criteo AI Lab, CREST IP Paris · Criteo AI Lab · ENSAE, Institut Polytechnique de Paris

May 30, 2026, cs.AIJ/K move · Enter open · S save

Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents

Yufeng Wang

AI Agent Reliability LLM Agent Evaluation LLM Decision-Making Agentic Reasoning LLM Reasoning

Open paper AskPDF arXiv

Do LLM agents act on the reasoning they state? This question of process fidelity is central to LLM-based social simulation, yet hard to measure where no reference for correct behavior exists. We study it in a controlled setting: a Texas Poker simulator with a verifiable reference action for every decision by splitting the faithfulness gap into two steps: reasoning-to-conclusion (does the stated decision follow from the agent's own reasoning?) and conclusion-to-action (does the agent execute what it states?). The two steps behave very differently. Conclusion-to-action is reliable: inconsistency is 0.7% for Claude Haiku 4.5 and 1.4% for DeepSeek-Reasoner once the conclusion is read from an explicit tag, whereas free-text conclusion extraction reports 22-26%. Reasoning-to-conclusion is where fidelity frays, but not through a single dominant failure. In a step-level diagnostic the agent's errors split roughly evenly between bad inputs, borderline cases, and rule misapplication deriving a conclusion that contradicts the agent's own restated rule from inputs it estimated correctly. This composition is model-dependent: rule misapplication accounts for a third of Haiku's interpretable errors but only 8% of DeepSeek's. The one robust signal is directional: when an agent does misapply its own stated rule, it almost always (99.5% for Haiku) errs in the risk-averse direction. The override is partly hedging behavior, not a capability limit: instructing the agent to apply the rule mechanically halves the misapplication rate (13.9% to 6.8% of decisions) and raises adherence by eight points. Process-fidelity evaluation should therefore elicit machine-checkable conclusions and probe for directional biases rather than assume a single upstream failure mode, lest it conflate measurement noise with model behavior.

Momentum

Related topics

Latest papers 650