LLM Reasoning

LLM: Large Language Model

This field asks how language models can carry out multi-step inference across mathematics, coding, logic, science, and real-world tasks, and how to tell robust reasoning from pattern matching. Common approaches include chain-of-thought prompting, self-consistency and tree search at inference time, tool use and symbolic verification, and post-training with supervised traces, reinforcement learning from verifiable rewards, or process feedback. Researchers are also exploring latent and recurrent computation to reduce reliance on long written traces, alongside benchmarks that test compositionality, robustness, and long-horizon execution. A central tension is that more computation can improve accuracy but raise cost, while plausible explanations and correct final answers do not by themselves establish faithful, reliable reasoning.

Latest papers

931 papers105 papers in the last four weeks, up 27% on the four weeks before. 0.6% of all new papers.

Broken Chains: The Cost of Incomplete Reasoning in LLMs
Feb 16, 2026Ian Su, Gaurav Purushothaman, Jey Narayan +5LLM Reasoning CoT Reasoning
Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models
Feb 16, 2026Mufan Xu, Kehai Chen, Xuefeng Bai +4RL for Language Model Reasoning Policy Optimization
School of Computer Science and Technology, Harbin Institute of Technology, China · Baidu Inc., Beijing, China
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
rePIRL: Learn PRM with Inverse RL for LLM Reasoning
Feb 8, 2026Xian Wu, Kaijie Zhu, Ying Zhang +2Reinforcement Learning Process Reward Models
Meta AI · Department of Computer Science, University of California, Santa Barbara · Independent Researcher +1
GR2: Generative Reasoning Re-ranker
Feb 8, 2026Mingfu Liang, Yufei Li, Jay Xu +20RL for Language Models RL for Recommendation
Meta AI
Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning
Feb 6, 2026Zhuoyuan Hao, Zhuo Li, Wu Li +3LLM Reasoning Large Reasoning Models
Harbin Institute of Technology, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · Huazhong University of Science and Technology, China
Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models
Feb 3, 2026Anish Sathyanarayanan, Aditya Nagarsekar, Aarush RathoreCoT Faithfulness Faithfulness of Language Model Explanations
BITS Pilani, K. K. Birla Goa Campus
Uncertainty Localization in LLM Reasoning via Embedding Perturbations
Feb 2, 2026Qihao Wen, Jiahao Wang, Yang Nan +3LLM Reliability LLM Uncertainty Estimation
University of Arizona · Michigan State University
Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning
Feb 2, 2026Yadong Wang, Haodong Chen, Yu Tian +3Sparse Autoencoders Continuous Latent Reasoning
Nanjing University of Aeronautics and Astronautics · State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 311215, China · Security Capability Center
Continuous-Utility Direct Preference Optimization
Jan 31, 2026Muhammad Ahmed Mohsin, Muhammad Umer, Emily FoxLLM Alignment Direct Preference Optimization
Stanford University, Stanford, California, USA
Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization
Jan 29, 2026Jiecong Wang, Hao Peng, Zhanyi Wang +2LLM Planning Efficient Language Model Reasoning
Beihang University · Didi Chuxing
Understanding LLM Failures: A Multi-Tape Turing Machine Analysis of Systematic Errors in Language Model Reasoning
Jan 27, 2026Magnus BomanTokenization in Language Models LLM Interpretability
Karolinska Institutet, Stockholm, Sweden
Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression
Jan 13, 2026Zijun Di, Bin Lu, Huquan Kang +5Text-Attributed Graph Learning LLM Reasoning
Shanghai Jiao Tong University Shanghai, China
Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
Jan 12, 2026Zhenghao He, Guangzhi Xiong, Bohan Liu +2LLM Interpretability CoT Reasoning
University of Virginia, USA
ChaosBench-Logic: A Benchmark for Logical and Symbolic Reasoning on Chaotic Dynamical Systems
Jan 5, 2026Noel ThomasSymbolic Reasoning in Language Models LLM Reasoning
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Entropy-Aware Token Rejection for Improving Speculative Decoding
Dec 29, 2025Tiancheng Su, Meicong Zhang, Guoxiu HeSpeculative Decoding LLM Inference Acceleration
School of Economics and Management East China Normal University
NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation
Dec 15, 2025Kei SaitoLLM Reasoning
Independent Researcher, Japan
Enhancing Large Language Model-Based Systems for End-to-End Circuit Analysis Problem Solving
Dec 10, 2025Liangliang Chen, Weiyu Sun, Huiru Xie +2LLM Answer Verification Educational Technology
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA
EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning
Nov 23, 2025Yogesh Kulkarni, Pooyan FazliEgocentric Video Understanding Video Reasoning
Arizona State University
Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles
Nov 8, 2025Fatima Jahara, Mark Dredze, Sharon LevyGender Bias in Language Models Language Model Bias Evaluation
Rutgers University · Johns Hopkins University
CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization
Nov 7, 2025Ziqian Bi, Yinzhi Wang, Tianyang Wang +6Efficient Language Model Reasoning LLM Inference Acceleration
1Purdue University, USA · 2Baruch College, City University of New York, USA · 3The Ohio State University, USA +6
Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results
Nov 7, 2025Jan-Thorsten Peter, David Vilar, Tobias Domhan +2Mathematical Reasoning Benchmarks Multilingual Language Model Evaluation
Google
Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems
Oct 28, 2025Yihan Li, Xiyuan Fu, Ghanshyam Verma +2Retrieval-Augmented Generation LLM Hallucination Mitigation
Electronic Information School, Wuhan University, Wuhan, China · School of Computing, Dublin City University, Dublin, Ireland · School of Public Health, Wuhan University, Wuhan, China +2
Learning to Reason Efficiently with Discounted Reinforcement Learning
Oct 27, 2025Alex Ayoub, Kavosh Asadi, Dale Schuurmans +2Reinforcement Learning RL for Language Model Reasoning
Amazon, University of Alberta · Amazon · University of Alberta
RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models
Oct 22, 2025Yang Yang, Hua XU, Zhangyi Hu +1Logistic Regression Neuro-Symbolic Reasoning
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511400, China · Institute of Deep Perception Technology, JITRI, Wuxi 214000, China
A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning
Oct 21, 2025Mengqi Li, Lei Zhao, Anthony Man-Cho So +2Self-Training for Language Models Mathematical Reasoning
The Chinese University of Hong Kong, Shenzhen · Shanghai Jiao Tong University · The Chinese University of Hong Kong
Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
Oct 15, 2025Buwei He, Yang Liu, Zhaowei Zhang +6Game Theory LLM Decision-Making
Beijing University of Posts and Telecommunications · Beijing Institute for General Artificial Intelligence · Peking University +1
Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
Oct 14, 2025Shouren Wang, Wang Yang, Xianxuan Long +4LLM Reasoning
Case Western Reserve University · Meta AI
Advancing the Pareto Frontier of Test-Time Scaling with Multi-Path Plan Aggregation
Oct 13, 2025Siheng Xiong, Ali Payani, Faramarz FekriTest-Time Scaling LLM Reasoning
Georgia Institute of Technology · Cisco Research

Feb 16, 2026J/K move · Enter open · S save

Broken Chains: The Cost of Incomplete Reasoning in LLMs

Ian Su, Gaurav Purushothaman, Jey Narayan, Ruhika Goel+4

LLM Reasoning CoT Reasoning Efficient Language Model Reasoning Constraint-Guided Reasoning in Language Models

Open paper AskPDF arXiv

Reasoning-specialized models like OpenAI's 5.1 and DeepSeek-V3.2 allocate substantial inference compute to extended chain-of-thought (CoT) traces, yet reasoning tokens incur significant costs. How do different reasoning modalities of code, natural language, hybrid, or none do perform under token constraints? We introduce a framework that constrains models to reason exclusively through code, comments, both, or neither, then systematically ablates token budgets to 10%, 30%, 50%, and 70% of optimal. We evaluate four frontier models (GPT-5.1, Gemini 3 Flash, DeepSeek-V3.2, Grok 4.1) across mathematical benchmarks (AIME, GSM8K, HMMT). Our findings reveal: (1) truncated reasoning can hurt as DeepSeek-V3.2 achieves 53% with no reasoning but only 17% with truncated CoT at 50% budget; (2) code degrades gracefully as Gemini's comments collapse to 0% while code maintains 43-47%; (3) hybrid reasoning underperforms single modalities; (4) robustness is model-dependent as Grok maintains 80-90% at 30% budget where OpenAI and DeepSeek collapse to 7-27%. These results suggest incomplete reasoning chains actively mislead models, with implications for deploying reasoning-specialized systems under resource constraints.