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

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning
Jul 11, 2026Ning LiuLLM Answer Verification Test-Time Scaling
Independent Researcher
CHASE: Cache-Hole-Adapted Skip Exit for Looped State-Space Language Models
Jul 11, 2026Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo +1Efficient Language Model Inference LLM Reasoning
Rikkyo University · The University of Tokyo
Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts
Jul 10, 2026Renuka Oladri, Mohan Vamsi Varadaraju Priya, Jerry WuLLM Quantization LLM Evaluation
Science Academy University of Maryland College Park, MD, USA · Electrical and Computer Engineering University of Maryland College Park, MD, USA
Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models
Jul 9, 2026Changhun Lee, Minguk Jeon, Jongkyung Shin +1Compositional Reasoning LLM Prompting
Columbia University · UNIST · POSCO Holdings
Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework
Jul 9, 2026Riccardo Revalor, Jalees Rehman, Debjit PalCoT Faithfulness LLM Reasoning with Graphs
¶Department of Electrical and Computer Engineering · ‡Department of Biochemistry and Molecular Genetics
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
Jul 8, 2026Ruilin Tong, Dong GongContinual Learning for LLMs Memory-Augmented Language Models
University of New South Wales (UNSW Sydney)
From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b
Jul 7, 2026Taeyun Roh, Eunha Lee, Wonjune Jang +3LLM Answer Verification Biomedical QA
Department of Computer Science and Engineering, Korea University, Seoul, 02841, Republic of Korea · Department of Mathematics, Myongji University, Yongin, 17058, Republic of Korea · 3AIGEN Sciences, Seoul, 04778, Republic of Korea
Mechanism-level routing failure in LLMs over Lean-verified algebraic structures
Jul 5, 2026Manuel Israel Cázares, Wenlin Zhang, Haobo MaLLM Reliability LLM Routing
Bytepro AI, Mazatlán, México · National University of Singapore / Omega Institute · ChronoAI / Omega Institute
dOPSD: On-Policy Self-Distillation for Diffusion Language Models
Jul 5, 2026Phuong Tuan Dat, Qi Li, Xinchao WangOn-Policy Self-Distillation Language Model Distillation
National University of Singapore
Reward-Gated On-Policy Distillation
Jul 4, 2026Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3Language Model Distillation On-Policy Distillation
University of Cologne · AWS AI · UT Austin +1
Reading Between the Dots: Decoding Hidden Computation across Filler Tokens
Jul 3, 2026Kaley Brauer, Claudio Mayrink Verdun, Samuel MarksLLM Auditing LLM Interpretability
Harvard University · 4Anthropic
OmniLayout: A Schematic-Coupled Multimodal Benchmark for Constraint-Aware Geometric Reasoning in PCB Layout
Jul 3, 2026Taiting Lu, Kaiyuan Lin, Mingjia Wang +12Electronic Design Automation Spatial Reasoning
Pennsylvania State University · Shanghai Jiao Tong University · Independent Researcher +2
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
Jul 2, 2026Dingling Xu, Ruobing Wang, Qingfei Zhao +8LLM Reliability LLM Reasoning
School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China · Beijing Key Laboratory of Artificial Intelligence for Education, Beijing 100875, China · Institute of Information Engineering, Chinese Academy of Sciences +3
Purified OPSD: On-Policy Self-Distillation Without Losing How to Think
Jul 2, 2026Zhanming Shen, Jintao Tong, Shaotian Yan +9CoT Distillation On-Policy Self-Distillation
1Zhejiang University · 2Tongyi Lab, Alibaba Group · 3Huazhong University of Science and Technology +1
TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B
Jul 2, 2026Baran Bingol, Bahaeddin TurkogluLLM Fine-Tuning LLM Mathematical Reasoning
Department of Artificial Intelligence and Data Engineering Faculty of Engineering Ankara University Ankara, Türkiye
Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness
Jul 2, 2026Aria Masoomi, Mahsa Bazzaz, Adel Javanmard +1LLM Evaluation Representation Geometry in Language Models
1Northeastern University · University of Southern California · 3Google Research
IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs
Jul 1, 2026Samir Abdaljalil, Erchin Serpedin, Hasan KurbanLLM Evaluation Scientific Reasoning
Electrical and Computer Engineering Texas A&M University College Station, TX USA · College of Science and Engineering Hamad Bin Khalifa University Doha, Qatar
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
Jul 1, 2026Chia-Hsuan Lee, Sihui Dai, Mingyang Zhou +4LLM Self-Correction Overthinking in Language Models
Capital One
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Jun 30, 2026Bytedance SeedLLM Evaluation Instruction Following
Bytedance Seed
Technical Report of RoboSpatial Challenge at CVPR 2026: Selective Reasoning Activation and Reference-Frame Disambiguation for Embodied Spatial Reasoning
Jun 30, 2026Yuxiang Xie, Qi Lv, Jianming Xing +4Visual Spatial Reasoning VLM Reasoning
1Harbin Institute of Technology, Shenzhen · 2Ruoyu Technology
Fork-Think with Confidence
Jun 30, 2026Zena Al-Khalili, Rafi Hakim, Dietrich Klakow +1LLM Inference Efficiency Efficient Language Model Reasoning
Saarland Informatics Campus, Saarland University, Germany
Spatial Reasoning via Modality Switching Between Language and Symbolic Representations
Jun 30, 2026Shreya Rajpal, Tanawan Premsri, Parisa KordjamshidiMultimodal Grounding Multimodal Reasoning
Department of Computer Science and Engineering Michigan State University Michigan, USA
BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation
Jun 29, 2026Ankur Samanta, Akshayaa Magesh, Tal Lancewicki +7LLM Evaluation Bayesian Inference
Meta AI · Columbia University · Work done at Meta +2
Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters
Jun 29, 2026Wenlong Wang, Fergal ReidLLM Prompting CoT Reasoning
Fin AI Research
NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries
Jun 29, 2026Aydin Javadov, Shyngys Aitkazinov, Tobias Hoesli +3Cognitive Modeling LLM Prompting
1ETH Zürich · 2Imperial College London · 3Technical University of Munich
HippoSpark: An On-Demand Experience System for LLM Reasoning
Jun 29, 2026Jingyao Liu, Danling Meng, Chen Huang +5Retrieval-Augmented Generation Memory-Augmented Language Models
College of Computer Science, Sichuan University · Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, China · College of Software Engineering, Sichuan University +3
Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
Jun 29, 2026Shuochen Chang, Qingyang Liu, Shaobo Wang +8LLM Interpretability Efficient Language Model Reasoning
Shanghai Jiao Tong University · Tongji University
LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents
Jun 28, 2026Mingyu Jeon, Bokyeong Kim, Suwan Cho +2Retrieval-Augmented Generation Legal Document Analysis
1MODULABS, Seoul, Republic of Korea · 2Korea Atomic Energy Research Institute, Daejeon, Republic of Korea · University of Science & Technology, Daejeon, Republic of Korea
The Complexity Ceiling Benchmark: A Multi-Domain Evaluation of Sequential Reasoning Under Depth Scaling
Jun 28, 2026Shubh Chapra, Dhruv Kumar, Murari Mandal +1LLM Evaluation Structured Reasoning
BITS Pilani, Pilani Campus · KIIT Bhubaneswar
ThinkProbe: Beyond Accuracy -- Structural Profiling of Open-Ended LLM Reasoning Traces via Non-Generative Thought Graphs
Jun 27, 2026Mohamed Amine Kerkouri, Simon D. Hernandez, Marouane Tliba +3LLM Reasoning with Graphs Structured Reasoning
F-Initiatives, Paris, France · Université sorbonne Paris Nord, Villetaneuse , France

Jul 11, 2026, cs.LGJ/K move · Enter open · S save

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

Ning Liu

Independent Researcher

LLM Answer Verification Test-Time Scaling Multi-Agent Consensus Language Model Ensembles LLM Reasoning

Open paper AskPDF arXiv

Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution. We study a third signal, free at inference time: cross-model consensus, the degree to which independently trained models, each solving the problem once, agree on a final answer. We treat the panel as an LLM-jury, in which the structure of agreement, not any model's score of another, is the verification signal. Across seven benchmarks it selects correct answers better than self-consistency and far better than a model scoring its own candidates: on competition math it closes the entire gap to an oracle selector, while self-scoring closes almost none. The mechanism is error decorrelation: independently trained models err differently, so their wrong answers scatter while the correct one accumulates agreement. We make this precise with a parameter-free law, derived in closed form, that predicts consensus accuracy from three measured panel statistics to a mean absolute error of

0.03

and exposes the method's ceiling: a shared-error floor where models share a misconception, near zero on math but non-trivial on science. Against four trained verifiers spanning discriminative, outcome, and generative reward models, the free LLM-jury matches the strongest inside their math training domain and is the top selector outside it. Cross-model consensus is thus a verifier we can characterize in advance: a law that says when to trust it, and a floor that marks where it cannot.

Momentum

Related topics

Latest papers 650