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

LLM Reasoning Is Latent, Not the Chain of Thought
Apr 17, 2026Wenshuo WangLLM Interpretability CoT Reasoning
School of Future Technology, South China University of Technology, China
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
Apr 16, 2026Kiran Purohit, Ramasuri Narayanam, Soumyabrata PalLLM Answer Verification Speculative Decoding
IIT Kharagpur · Adobe Research
IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning
Apr 16, 2026Zihan Liang, Yufei Ma, Ben Chen +6Retrieval-Augmented Generation RL for Language Model Reasoning
Kuaishou Technology
IE as Cache: Information Extraction Enhanced Agentic Reasoning
Apr 16, 2026Hang Lv, Sheng Liang, Hongchao Gu +5Agentic Reasoning LLM Information Extraction
University of Science and Technology of China · Huawei Technologies Co., Ltd.
Governing Reflective Human-AI Collaboration: A Framework for Epistemic Scaffolding and Traceable Reasoning
Apr 16, 2026Rikard Rosenbacke, Carl Rosenbacke, Victor Rosenbacke +1AI Governance Human-AI Collaboration
Faculty of Medicine, Lund University, Sweden · Department of Economics, Lund University School of Economics and Management, Sweden · Department of Health Services Research and Policy, London School of Hygiene & Tropical Medicine, UK
Dissecting Failure Dynamics in Large Language Model Reasoning
Apr 16, 2026Wei Zhu, Jian Zhang, Lixing Yu +2Inference-Time Guidance LLM Reasoning
School of Information Science and Engineering, Yunnan University, Kunming, China · Yunnan Key Laboratory of Intelligent Systems and Computing, Kunming, China
Quantifying Cross-Query Contradictions in Multi-Query LLM Reasoning
Apr 16, 2026Rohit Kumar Salla, Ramya Manasa Amancherla, Manoj SaravananLLM Reasoning
Virginia Tech · Columbia University
Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis
Apr 15, 2026Zipeng Ling, Shuliang Liu, Seonil Son +4Logical Reasoning Self-Consistency Decoding
The Hong Kong University of Science and Technology (Guangzhou) · University of Alberta · Alberta Machine Intelligence Institute +3
How LLMs Might Think
Apr 2, 2026Joseph Gottlieb, Ethan Kemp, Matthew TragerLLM Reasoning
Dept. of Philosophy, Texas Tech University · Dept. of Philosophy, New York University · Dept. of History and Philosophy of Science, University of Pittsburgh, Matthew Trager
Reasoning Shift: How Context Silently Shortens LLM Reasoning
Apr 1, 2026Gleb Rodionov, Roman Garipov, George YakushevLanguage Model Robustness LLM Context Management
Yandex · HSE University
SafeMath: Safe Solutions for Unsafe Math Word Problems
Mar 26, 2026Sagnik Basu, Subhrajit Mitra, Aman Juneja +3LLM Safety Alignment LLM Safety Evaluation
1Indian Institute of Technology Kharagpur · 2Cisco Systems · 3National University of Singapore
Thinking Deeper, Not Longer: Memory-Efficient Test-Time Reasoning with Depth-Recurrent Transformers for Compositional Generalization
Mar 23, 2026Hung-Hsuan ChenEfficient Transformer Inference Recurrent Transformers
Computer Science and Information Engineering National Central University Taoyuan, Taiwan
Beyond Memorization: Distinguishing Between Pattern-Based and Epistemic Reasoning in LLMs Using Epistemic Puzzles
Mar 22, 2026Adi Gabay, Gabriel Stanovsky, Liat PeterfreundEpistemic Logic LLM Reasoning
School of Computer Science and Engineering The Hebrew University of Jerusalem
Grounded Chess Reasoning in Language Models via Master Distillation
Mar 20, 2026Zhenwei Tang, Qianfeng Wen, Seth Grief-Albert +4LLM Grounding CoT Distillation
Department of Computer Science, University of Toronto · Queen’s University · Coolwei AI Lab
Learning Dynamic Belief Graphs for Theory-of-mind Reasoning
Mar 20, 2026Ruxiao Chen, Xilei Zhao, Thomas J. Cova +2Computational Cognitive Modeling LLM Reasoning with Graphs
Department of Civil and Systems Engineering, Johns Hopkins University, Baltimore, MD, USA · Civil and Coastal Engineering, University of Florida, Gainesville, FL, USA · School of the Environment, Society & Sustainability, University of Utah, Salt Lake City, UT, USA +1
Can LLMs Prove Robotic Path Planning Optimality? A Benchmark for Research-Level Algorithm Verification
Mar 19, 2026Zhengbang Yang, Md. Tasin Tazwar, Minghan Wei +1Mathematical Reasoning Benchmarks Automated Theorem Proving
George Mason University. · Florida Atlantic University.
ZEBRAARENA: A Diagnostic Simulation Environment for Studying Reasoning-Action Coupling in Tool-Augmented LLMs
Mar 19, 2026Wanjia Zhao, Ludwig Schmidt, Yejin Choi +3LLM Evaluation AI Agent Benchmarks
Stanford University · Microsoft Research
RAWR: Reward Assignment Without Rollouts in Verifiable Domains
Mar 18, 2026Corentin Royer, Anna Hedström, Debarun Bhattacharjya +3Process Reward Models Reinforcement Learning with Verifiable Rewards
International Business Machines · Department of Computer Science, ETH Zurich, 8092 Zurich, Switzerland · ETH AI Center +2
Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation
Mar 16, 2026Yanick Zengaffinen, Andreas Opedal, Donya Rooein +3LLM Prompting Generative AI in Education
1ETH Zürich · 2Bocconi University · University of Central Florida
RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction
Mar 13, 2026Hanbum Ko, Chanhui Lee, Ye Rin Kim +4AI-Assisted Scientific Research Language Modeling
Department of Artificial Intelligence, Korea University · Materials Intelligence Lab, LG AI Research · Department of Statistics, Korea University
HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation
Mar 11, 2026Wenjing Zhang, Jiangze Yan, Jieyun Huang +7CoT Distillation Language Model Distillation
Data Science & AI Research Institute, China Unicom · Unicom Data Intelligence, China Unicom
EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
Mar 10, 2026Chengjun Yu, Xuhan Zhu, Chaoqun Du +4Multimodal Large Language Models Egocentric Video Understanding
University of Science and Technology of China · Foundation Model Team, Li Auto Inc. · Tsinghua University
Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning
Mar 9, 2026Juming Xiong, Kevin Guo, Congning Ni +7CoT Reasoning Efficient Language Model Reasoning
1Vanderbilt University · 2Vanderbilt University Medical Center · 3Intuit AI Research
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
Mar 5, 2026Hejian Sang, Yuanda Xu, Zhengze Zhou +3CoT Distillation Efficient Language Model Reasoning
Verify to Amplify: Improving Reasoning via Learned Chain-of-Thought Verification
Mar 3, 2026Maria-Florina Balcan, Avrim Blum, Kiriaki Fragkia +2LLM Evaluation LLM Answer Verification
Carnegie Mellon University · Toyota Technological Institute at Chicago · Northwestern University
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Mar 3, 2026Xuan Yang, Jiayu Liu, Yuhang Lai +3LLM Interpretability Sparse Autoencoders
Department of Data Science, City University of Hong Kong · Hong Kong Institute of AI for Science, City University of Hong Kong · Li Auto Inc +1
Recursive Models for Long-Horizon Reasoning
Mar 2, 2026Chenxiao Yang, Nathan Srebro, Zhiyuan LiLong-Context Modeling Language Modeling
Toyota Technological Institute at Chicago
Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs
Feb 18, 2026Felix Fricke, Simon Malberg, Georg GrohInference-Time Optimization Tree of Thoughts
School of Computation, Information and Technology Technical University of Munich
Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
Feb 13, 2026Wei-Lin Chen, Liqian Peng, Tian Tan +5LLM Inference Efficiency Inference-Time Scaling
University of Virginia · Google
Discovering High Level Patterns from Simulation Traces
Feb 10, 2026Sean Memery, Kartic SubrLLM Grounding Program Synthesis
University of Edinburgh, United Kingdom

Apr 17, 2026, cs.AIJ/K move · Enter open · S save

LLM Reasoning Is Latent, Not the Chain of Thought

Wenshuo Wang

School of Future Technology, South China University of Technology, China

LLM Interpretability CoT Reasoning LLM Reasoning Latent Reasoning

Open paper AskPDF arXiv

This position paper argues that large language model (LLM) reasoning should be studied as latent-state trajectory formation rather than as faithful surface chain-of-thought (CoT). This matters because claims about faithfulness, interpretability, reasoning benchmarks, and inference-time intervention all depend on what the field takes the primary object of reasoning to be. We ask what that object should be once three often-confounded factors are separated and formalize three competing hypotheses: H1, reasoning is primarily mediated by latent-state trajectories; H2, reasoning is primarily mediated by explicit surface CoT; and H0, most apparent reasoning gains are better explained by generic serial compute than by any privileged representational object. Reorganizing recent empirical, mechanistic, and survey work under this framework, and adding compute-audited worked exemplars that factorize surface traces, latent interventions, and matched budget expansions, we find that current evidence most strongly supports H1 as a default working hypothesis rather than as a task-independent verdict. We therefore make two recommendations: the field should treat latent-state dynamics as the default object of study for LLM reasoning, and it should evaluate reasoning with designs that explicitly disentangle surface traces, latent states, and serial compute.

Momentum

Related topics

Latest papers 650