LLM Mathematical Reasoning

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 375% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 194

All topics

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve
Aug 4, 2026Denys Pushkin, Albert Q. Jiang, Aryo Lotfi +2LLM Prompting CoT Reasoning
EPFL · Apple · Mistral AI
A Human Audit of OpenAIs AI-Generated Mathematical Proofs
Aug 3, 2026Mikołaj Sienicki, Krzysztof SienickiLLM Auditing Human Oversight of AI
Polish-Japanese Academy of Information Technology ul. Koszykowa 86, 02-008 Warsaw, Poland, European Union · Chair of Theoretical Physics of Naturally Intelligent Systems (NIS)1 ul. Lipowa 2 / Topolowa 19, 05-807 Podkowa Leśna, Poland, European Union
Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning
Aug 3, 2026Xuyang Zhao, Liting Zhang, Zichen Xu +4On-Policy Self-Distillation Knowledge Representation
1TMCC, College of Computer Science, Nankai University, Tianjin, China · 2Huawei Technologies Ltd., Beijing, China
Cloud-ScPO: Hidden-State Geometry for Semi-Supervised Preference Optimization in LLM Reasoning
Aug 2, 2026Yuzhou Liu, Xiyang HuPreference Optimization Semi-Supervised Learning
University of Southern California · Arizona State University
Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs
Aug 1, 2026Zhenhong Sun, Hanqing Zhao, Yatao Bian +7Test-Time Scaling Diffusion Language Model Decoding
Australian National University Canberra, Australia · Nanyang Technological University Singapore · National University of Singapore Singapore +2
AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction
Jul 31, 2026Rui Zou, Yutao Zhu, Mengqi Wei +1LLM Self-Correction LLM Answer Verification
Gaoling School of Artificial Intelligence, Renmin University of China · National Engineering Research Center of Educational Big Data, Central China Normal University
Albilich: Steerable Proof-State Orchestration for LLM-Based Mathematical Research with CAS Integration
Jul 30, 2026Ting Gong, Michael Ruofan Zeng, Yong YangAutomated Theorem Proving AI-Assisted Scientific Research
University of Washington Seattle, Washington, USA · Texas State University San Marcos, Texas, USA
ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning
Jul 30, 2026Zhenrong Zhang, Fei Wu, Jun Du +2RL for Language Model Reasoning Credit Assignment in RL
1IFLYTEK Research · University of Science and Technology of China
A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models
Jul 28, 2026Vivek Shukla, Varun Shukla, Atul +2CoT Faithfulness Mathematical Reasoning Benchmarks
Allenhouse Institute of Technology Kanpur, India
Case study: proving sqrt(2) irrational with LPTP and an LLM
Jul 23, 2026Fred Mesnard, Étienne Payet, Wim VanhoofAutomated Theorem Proving LLM Mathematical Reasoning
LIM, université de La Réunion, France · Université de Namur, Belgium
Mathematical Discovery in the Wild: AI-Guided Proofs in Banach Space Theory
Jul 19, 2026Antonio Acuaviva, Pablo AcuavivaAutomated Theorem Proving AI-Assisted Scientific Research
Explaining and Tuning Transformer-based LLMs in Arithmetic Tasks with Human Strategies
Jul 19, 2026Luyu Qiu, Jianing Li, Hwanhee Kim +4Transformer Interpretability Language Modeling
1The Hong Kong University of Science and Technology · 2The Hong Kong Polytechnic University · University of California, Berkeley
Trace-Based On-Policy Distillation for Masked Diffusion Language Models
Jul 18, 2026Haolin Ren, Ziyang Huang, Chenhao Yuan +2Masked Diffusion Models Diffusion Model Distillation
Institute of Automation, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs
Jul 18, 2026Sharath Naganna, Tanvir Ahmed Sijan, Uddipta KalitaLLM Interpretability Circuits in Language Models
Indian Institute of Technology Bombay, Mumbai, India · Jahangirnagar University, Dhaka, Bangladesh · National Institute of Technology, Silchar, India
CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA
Jul 16, 2026Quoc-Khang Tran, Minh-Thien Nguyen, Phu-An Thai +3Explainable Artificial Intelligence LLM-Based Program Synthesis
Can Tho University, Can Tho city, Vietnam · Tay Do University, Can Tho city, Vietnam
MathCoPilot: An Interactive System for Human-AI Symbiotic Paradigm of Mathematical Research
Jul 16, 2026Junjie Zhang, Jiayu Liu, Wenbin Liu +11Multi-Agent LLM Systems Automated Theorem Proving
1State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China · School of Mathematical Sciences, University of Science and Technology of China
GSM-Plus-BN: A Perturbation-Based Benchmark for Bangla Mathematical Reasoning in Large Language Models
Jul 14, 2026Bidyarthi Paul, Nahida Jannat Mayouree, Md. Asif Karim +2Mathematical Reasoning Benchmarks Multilingual Language Model Evaluation
Computer Science and Engineering Southeast University Dhaka, Bangladesh · Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka, Bangladesh
AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification
Jul 13, 2026Lingkai Kong, Zijian Wu, Yuzhe Gu +11Mathematical Reasoning Benchmarks Automated Theorem Proving
Shanghai AI Laboratory · Shanghai Jiao Tong University · MMLab, The Chinese University of Hong Kong +1
TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs
Jul 13, 2026Burak S. Akbudak, Zeynel A. Uluşan, Can S. Erer +1Automated Theorem Proving Tree Search
Computer Engineering Department, Bogazici University, Istanbul, Turkey · Computer Engineering Department, Koç University, Istanbul, Turkey · Codeway Studios, Istanbul, Turkey +2
ProofCouncil: An LLM Agent for Solving Open Mathematical Problems
Jul 10, 2026Johannes Schmitt, Tim Gehrunger, Jasper Dekoninck +4LLM Agents Multi-Agent LLMs
ETH Zurich · Aarhus University · Independent Researcher +1
From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier
Jul 8, 2026Eric Jiang, Xiao Liang, Yikai Zhang +16Automated Theorem Proving Interactive Theorem Proving
University of California, Los Angeles · 2Lawrence Livermore National Laboratory
MIRA-Math: A Benchmark for Minimal Information Requesting and Mathematical Reasoning
Jul 8, 2026Charbel Al Bateh, Samer SaabMathematical Reasoning Benchmarks Synthetic Benchmark Generation
Department of Electrical and Computer Engineering Lebanese American University Byblos, Lebanon
Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits
Jul 8, 2026Zitong Andrew Chen, Junaid Hasan, Akhil Srinivasan +2Transformer Interpretability Transformer Attention
1UW Math AI Lab, University of Washington.
Evaluating SageMath-Augmented LLM Agents for Computational and Experimental Mathematics
Jul 7, 2026Pavel Snopov, German MagaiMathematical Reasoning Benchmarks Knowledge Augmentation for Language Models
School of Mathematical and Statistical Sciences, The University of Texas Rio Grande Valley, USA · Noeon Research, Tokyo, Japan.
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Jul 7, 2026Jihao Liu, Guoxiong Gao, Zeming Sun +8Agent Memory Multi-Agent Orchestration
School of Mathematical Sciences, Peking University · Beijing International Center for Mathematical Research, Peking University · Research Institute for Mathematical Sciences, Kyoto University +8
PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages
Jul 7, 2026Daryna Dementieva, Nikolay Babakov, Kathy Hämmerl +14Mathematical Reasoning Benchmarks Multilingual Language Model Evaluation
Technical University of Munich (TUM) · Munich Center for Machine Learning (MCML) · Independent Researcher +7
Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs
Jul 6, 2026Nikolaos Xiros, Maria-Eleni Zoumpoulidi, Georgios ParaskevopoulosHallucination in Language Models Representation Geometry in Language Models
Institute for Language and Speech Processing, Athena Research Center, Greece
SPL: Orchestrating Workflows with Declarative Deterministic-Probabilistic Composition
Jul 6, 2026Wen G. GongLLM Agent Orchestration Neuro-Symbolic AI
Independent Researcher
Detecting Answer-Driven Reasoning in LLM-Based Educational Tutors via Truncated Chain-of-Thought Auditing
Jul 6, 2026Bonan Shen, Dingyan Shang, Youting Wang +1CoT Faithfulness Intelligent Tutoring Systems
Independent Researcher United States · Northeastern University Boston, MA, USA · Syracuse University Syracuse, NY, USA
MechMath Agent Team: LLM Driven Agents for Mathematical Research
Jul 5, 2026Yichuan Cao, Ruichen Qiu, Junqi Liu +5Automated Theorem Proving Multi-Agent Reasoning
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, CAS · School of Mathematical Sciences, University of Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences

Aug 4, 2026, cs.AIJ/K move · Enter open · S save

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve

Denys Pushkin, Albert Q. Jiang, Aryo Lotfi, Colin Sandon+1

EPFL · Apple · Mistral AI

LLM Prompting CoT Reasoning Few-Shot Prompting LLM Mathematical Reasoning

Open paper AskPDF arXiv

Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities. Originally, this technique was introduced to elicit step-by-step reasoning from large language models (LLMs), which would otherwise tend to directly output the final answer. However, many modern LLMs produce CoT-style responses \textit{natively} when presented with reasoning tasks, which made us revisit the effectiveness of standard CoT prompting. We evaluate several modern mid-sized language models on a math problem-solving task and find that models specialized for reasoning achieve better performance in a simple zero-shot setting than when using few-shot CoT examples - significantly surpassing officially reported results at no additional cost (e.g., from

\sim

77% to

\sim

84% for Mathstral on GSM8K). For the tested general-purpose model, a zero-shot CoT prompt is also sufficient to outperform a few-shot CoT baseline. We attribute this to a `guidance-distraction' tradeoff: standard CoT prompting also demands style adaptation, formatting compliance, and potentially undesired contextualization, which can distract models from the core reasoning task. Our findings suggest that using standard CoT prompting increasingly acts as a source of distraction as models grow stronger.

Momentum

Related topics

Latest papers 194