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.

Rethinking Neural Thickets Without Weight Perturbations
Oct 29, 2026Nicolas Dufour, Elouan Gardès, Amil Dravid +2LLM Reasoning Ensemble Learning
Kyutai · Meta FAIR · LIGM, CNRS, Univ Gustave Eiffel, ENPC, IP Paris +2
Latent Path Exploration via Potential-Guided Subtrajectory Balance
Oct 29, 2026Xiaoling Zeng, Qi ZhangLLM Reasoning Continuous Latent Reasoning
Worcester Polytechnic Institute
MASS: Multi-mask Selective Self-Distillation for Leakage-Resilient Reasoning
Oct 28, 2026Xiuqi Liu, Oveys Delafrooz Noroozi, Upamanyu MadhowLanguage Model Distillation Selective Knowledge Distillation
Chongqing Bashu Secondary School · University of California, Santa Barbara
Think Twice: The Metis-1.6 Technical Report
Oct 27, 2026Giulianno VollmerLLM Training Efficient Language Model Training
Lernex Research
Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards
Oct 27, 2026Bo Yang, Zishuai Zhang, Weihua Li +3RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University · School of Artificial Intelligence, Beihang University
Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning Traces
Oct 27, 2026Pragna MallappaLLM Reasoning Language Model Reasoning Evaluation
Keshav Memorial Institute of Technology
DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models
Oct 26, 2026Hongze Chen, Miao Pan, Lizhou Liang +7Diffusion Language Model Training RL for Diffusion Models
Zhejiang University · National University of Singapore · SAP
GIFT: Gradient Informed Filtering for Distillation Augmented Reasoning RL
Oct 22, 2026Shijie Li, Yilin Gao, Tieyuan Chen +3RL for Language Model Reasoning LLM Reasoning
Shanghai Jiao Tong University · Tencent
TraceForge: Distilling with Your Own Thinking
Oct 21, 2026Yan WangCoT Distillation LLM Reasoning
Independent Researcher
TeachBack: Learning to Teach via Bidirectional Preference Optimization for On-Policy Self-Distillation
Oct 21, 2026Linfei Ji, Jiayun Li, Haozhao Wang +5Language Model Distillation On-Policy Self-Distillation
Huazhong University of Science and Technology · Tsinghua University · Harbin Institute of Technology +1
NormTune: Norm-Guided Parameter-Efficient Fine-Tuning for Reasoning-Intensive Tasks
Oct 21, 2026Zhangming Li, Qinghao Hu, Weifan Guan +3Fine-Tuning Language Models Parameter-Efficient Fine-Tuning
1The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · 3AiRiA +1
When Can LLM Reasoning Reliably Reuse Intermediate Results?
Oct 20, 2026Deyuan Liu, Zecheng Wang, Xuanyi Liu +5LLM Reasoning Efficient Language Model Reasoning
Westlake University · Wechat AI · Peking University +3
RESIN: Multi-Chain Reasoning with Entity-Structured Indexing
Oct 19, 2026Xuanyu Meng, Jash Rajesh Parekh, Jiawei HanLLM Reasoning Retrieval-Augmented Reasoning
University of Illinois Urbana-Champaign
Understanding When Reflective Prompt and Skill Optimization Helps on Locally Served Reasoning Models: A Two-Model Study of GEPA and SkillOpt
Oct 19, 2026Andrea Giummarra, Carmelo Baglieri, Antonio Di Maria +3LLM Input Optimization Large Language Model-Guided Optimization
Evision srl, Ragusa, Italy · Department of Clinical and Experimental Medicine, University of Catania, Catania, Italy
Keep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM Decoding
Oct 19, 2026Minoo Ahmadi, Seyedarmin Azizi, Mehdi Kamal +1Language Model Decoding Diffusion Language Model Decoding
University of Southern California, Los Angeles, USA
LOOP: Recovery-Aligned Iterative Layer Pruning via On-Policy Distillation
Oct 19, 2026Liang Xu, Shufan Shen, Zhongni Hou +4LLM Pruning Neural Network Pruning
State Key Lab. of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Meituan
When Form Changes but Logic Doesn't: Building Logic-invariant LLMs through Logical Structure
Oct 18, 2026Xuyuan Liu, Xinshuai Dong, Elynn Chen +1LLM Reasoning Structured Reasoning in Language Models
Dartmouth College · Carnegie Mellon University · New York University
Where and Why Search-Augmented LLMs Fail When Reasoning over Rapidly Evolving Knowledge
Oct 18, 2026Tianyi Hu, Bhavyajeet Singh, Niket Tandon +1Retrieval-Augmented Reasoning LLM Reasoning
Aarhus University · Microsoft Research · Technische Universität Darmstadt
Conformal Prediction-Enabled Sequence-level Policy Optimization for Reasoning Language Models
Oct 18, 2026Hui Yang, Wan Tian, Tao Ren +2RL for Language Models RL for Language Model Reasoning
Peking University · Beihang University · Nanjing University
DeGMatch: Target-Aware Reasoning Data Selection via Deconfounded Gradient Matching
Oct 18, 2026Changho Lee, Janghoon Han, Rajdeep Mukherjee +4Data Selection for Language Model Fine-Tuning LLM Reasoning
University of Michigan · University of Texas at Dallas · LG AI Research
What RL Brings to Reasoning: A Few Decisions the Base Model Would Not Make
Oct 17, 2026Siyu Zhang, Yuquan Lu, Yoshua Y. Li +7RL for Language Model Reasoning LLM Reasoning
University of California, San Diego · Meituan, LongCat Team · The Chinese University of Hong Kong, Shenzhen
Preserving Reasoning Diversity in Reinforcement Learning with Verifiable Rewards via Adaptive Replay
Oct 16, 2026Wen-Zhi Li, Sainyam Galhotra, Claire CardieReinforcement Learning RL for Language Model Reasoning
Cornell University
Reasoning with Context Management and External Memory
Oct 16, 2026Man-Ling Sung, William Hartmann, Jiangying ZhouLLM Context Management Efficient Language Model Reasoning
RTX BBN Technologies, Cambridge MA, USA
Trajectory-Triggered Sparse Collaborative Decoding
Oct 16, 2026Amit Ranjan Trivedi, Sruthikesh Surineni, Kyong Ho Lee +3Speculative Decoding LLM Reasoning
University of Illinois Chicago · Meta
MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning
Oct 16, 2026Jihao Huang, Guangjia Chai, Zhirui Chen +9RL for Language Model Reasoning LLM Reasoning
Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design
Oct 16, 2026Benhao Huang, Chufan Shi, Junlin Chen +4Recurrent Transformers Recursive Language Models
Institute of Foundation Models · CMU · USC
Competence-Based Evaluation of Logical Reasoning in Large Language Models
Oct 16, 2026Jize Jiang, Chengxiang ZhaiLLM Evaluation LLM Reasoning
University of Illinois Urbana-Champaign
Bengali Hallucination Detection with Retrieval and Programs: A System Study
Oct 16, 2026Shamim Hasan, Samiya Ahmed ChowdhuryHallucination Detection LLM Hallucination Detection
Department of Computer Science and Engineering, BNIST, Dhaka, Bangladesh · Department of Computer Science and Engineering, Chittagong University of Engineering and Technology, Chittagong, Bangladesh
Are Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks
Oct 15, 2026Kentaro Ozeki, Risako Ando, Takanobu Morishita +3Language Model Reasoning Evaluation LLM Reasoning
Keio University
Learning from Unverified Peers via Shared Residual Distillation
Oct 15, 2026Feiyang Chen, Runze Ma, Zichen Wang +4Self-Training for Language Models Language Model Distillation
Shanghai Jiao Tong University

Oct 29, 2026J/K move · Enter open · S save

Rethinking Neural Thickets Without Weight Perturbations

Nicolas Dufour, Elouan Gardès, Amil Dravid, Patrick Pérez+1

Kyutai · Meta FAIR · LIGM, CNRS, Univ Gustave Eiffel, ENPC, IP Paris+2

LLM Reasoning Ensemble Learning

Open paper AskPDF arXiv

The Neural Thickets hypothesis posits that pretrained language models lie in dense neighborhoods of task-specific experts in weight space, which random Gaussian perturbations can uncover. We reproduce the reported gains, but show that they do not require this geometric explanation. Perturbing a single decoder block already recovers much of the improvement, while keeping the model entirely frozen and adding a random bias to its output logits matches or exceeds full-weight perturbations on most reasoning tasks. This suggests an alternative explanation based on output diversity, validation-based selection, and voting. We formalize this view as Perturb-Select-Vote (PSV), a general procedure that generates perturbed predictors, selects high-performing members on a small validation set, and aggregates their predictions. This interpretation connects Neural Thickets to established inference-time methods, including sampling, self-consistency, and verifier-guided selection. A first-order analysis further shows that small weight perturbations act primarily through their induced logit shifts. We extend this analysis to vision, where logit PSV substantially improves performance under domain shift, including on Earth observation, while full-weight perturbations provide little additional benefit. Together, these results suggest that the gains attributed to nearby weight-space experts can instead be obtained through output diversity, selection, and voting. Logit PSV realizes these benefits with a fully frozen model, providing a simple, training-free alternative to full-weight perturbation ensembles across language and vision.