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

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning
Jun 5, 2026Yongliang Miao, Fengyuan Liu, Wei Shi +4Supervised Fine-Tuning LLM Mathematical Reasoning
The Chinese University of Hong Kong, Shenzhen · Shanghai Artificial Intelligence Laboratory · New Jersey Institute of Technology +1
When to Think Deeply: Inhibitory Deliberation for LLM Reasoning
Jun 4, 2026Zhixuan He, Yue FengEfficient Language Model Reasoning Inference-Time Compute Allocation
University of Birmingham, United Kingdom
Benchmarks in Leipzig
Jun 4, 2026Andrei Balakin, Miklós Bóna, Marie-Charlotte Brandenburg +45Mathematical Reasoning Benchmarks LLM Evaluation
Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving
Jun 4, 2026Muhammad Talha Sharif, Abdul RehmanLLM Self-Correction Multi-Agent Reasoning
dept. of Computer Science · National University of Computer and Emerging Sciences · Islamabad, Pakistan
Evaluation of LLMs for Mathematical Formalization in Lean
Jun 4, 2026Tyson Klingner, Drew Bladek, Escher Crawford +6LLM Evaluation Lean Theorem Proving
Math AI Lab, University of Washington, Seattle, WA, USA. · Math AI Lab, University of Washington, Seattle, WA
Can AI Refute Economic Theory? Evidence from Beyond the Knowledge Cutoff
Jun 3, 2026Alexis Akira TodaHuman-in-the-Loop AI Automated Peer Review
Department of Economics, Emory University.
Arithmetic Pedagogy for Language Models
Jun 3, 2026Andhika Bernard Lumbantobing, Hokky SitungkirNumerical Reasoning in Language Models Language Model Pretraining
Bandung Fe Institute & Adjunct Science Fellow in InaAI · Adjunct Science Fellow in InaAI · AI Research Center IT Del +1
CrowdMath: A Dataset of Crowdsourced Mathematical Research Discussions
Jun 2, 2026Sherin Muckatira, Jesse Geneson, Slava Gerovitch +3Mathematical Reasoning Benchmarks LLM Mathematical Reasoning
University of Massachusetts Lowell · San Jose State University · 3Massachusetts Institute of Technology +2
PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models
Jun 2, 2026Zetian Ouyang, Linlin Wang, Gerard de Melo +1Numerical Reasoning in Language Models Mathematical Reasoning Benchmarks
East China Normal University · Hasso Plattner Institute, University of Potsdam
Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks
Jun 2, 2026Malia Barker, Bishal Lakha, Edoardo Serra +1Numerical Reasoning in Language Models Mathematical Reasoning Benchmarks
Department of Computer Science, Boise State University, Boise, ID, USA · University of L'Aquila, L'Aquila, Italy
Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning
Jun 2, 2026Ziyue Wang, Aomufei Yuan, Yongfu Zhu +10LLM Alignment RL for Language Model Reasoning
1Peking University · 2JINGDONG · 3Shanghai Innovation Institute +2
GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory
Jun 2, 2026Noujoud Nader, Ibrahem Aljabea, Patrick Diehl +1Mathematical Reasoning Benchmarks LLM Reasoning with Graphs
Louisiana State University, USA · Los Alamos National Laboratory, USA · Texas A&M-Central Texas, USA
eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion
Jun 1, 2026Xiang Li, Jiwei Wei, Ke Liu +5Memory-Augmented Language Models LLM Mathematical Reasoning
Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
Jun 1, 2026Atoosa Chegini, Soheil FeiziNumerical Reasoning in Language Models Inference-Time Search
Department of Computer Science, University of Maryland
AXIOM: A Trust-First Neuro-Symbolic Execution Architecture for Verifiable Mathematical Reasoning
May 30, 2026Alessio BrunoLLM Answer Verification Symbolic Reasoning
Independent researcher
KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning
May 30, 2026Jayant Parashar, Suchendra M. BhandarkarMemory-Augmented Language Models Self-Consistency Decoding
School of Computing University of Georgia
The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models
May 29, 2026Liuyuan Wen, Xun Zhu, Lihao Huang +2Neural Representation Geometry LLM Interpretability
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210023, China.
COMPOSE: Composing Future Theorems from Citations and Formal Structure
May 28, 2026David Busbib, Michael WermanGraph Retrieval-Augmented Generation Evidence-Grounded Generation
Hebrew University of Jerusalem
Knowing What to Solve Before How: Preplan Empowered LLM Mathematical Reasoning
May 28, 2026Shaojie Wang, Liang ZhangLLM Planning Structured Reasoning
Hong Kong University of Science and Technology (Guangzhou)
DenseSteer: Steering Small Language Models towards Dense Math Reasoning
May 28, 2026Yang Ouyang, Shuhang Lin, Jung-Eun KimSmall Language Models Activation Steering
1North Carolina State University · 2Rutgers University
When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer
May 28, 2026Mayug Maniparambil, Arjun Karuvally, Terrence Sejnowski +1RL for Language Models RL for Language Model Reasoning
Fin AI Research · Salk Institute for Biological Studies
On Compositional Learning Behaviours in Formal Mathematics
May 27, 2026Kevin Yandoka DenamganaïMathematical Reasoning Benchmarks Formal Verification
University of York
FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning
May 27, 2026Haihui Pan, Junwei Bao, Hongfei Jiang +1LLM Answer Verification RL for Language Model Reasoning
Zuoyebang Education Technology
Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning
May 27, 2026Pauline Bourigault, Xiaotong Ji, Matthieu Zimmer +2LLM Answer Verification Selective Prediction
Imperial College London · Huawei Noah’s Ark Lab · UCL Centre for AI
ResearchMath-14K: Scaling Research-Level Mathematics via Agents
May 27, 2026Guijin Son, Seungyeop Yi, Minju Gwak +3Supervised Fine-Tuning LLM Mathematical Reasoning
Seoul National University · OneLineAI · Yonsei University
Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphs
May 26, 2026Jiaqiao Zhang, Zhoujun Li, Raoyuan Zhao +5Mathematical Reasoning Low-Resource Language Processing
Southwest University · LMU Munich & MCML
ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation
May 26, 2026Raoyuan Zhao, Yihong Liu, Yupei Du +2Mathematical Reasoning Benchmarks Synthetic Benchmark Generation
Center for Information and Language Processing, LMU Munich · 2Munich Center for Machine Learning (MCML) · 3Saarland University
Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions
May 26, 2026Matthew KutakhCoT Reasoning Mathematical Reasoning
Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning
May 23, 2026Haizhou XiaLLM Self-Correction LLM Mathematical Reasoning
Advancing Mathematics Research with AI-Driven Formal Proof Search
May 21, 2026George Tsoukalas, Anton Kovsharov, Sergey Shirobokov +18Automated Theorem Proving AI Agent Evaluation
1Google DeepMind1 · 2Aarhus University · 3Google

Jun 5, 2026, cs.LGJ/K move · Enter open · S save

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

Yongliang Miao, Fengyuan Liu, Wei Shi, Yanguang Liu+3

The Chinese University of Hong Kong, Shenzhen · Shanghai Artificial Intelligence Laboratory · New Jersey Institute of Technology+1

Supervised Fine-Tuning LLM Mathematical Reasoning LLM Reasoning

Open paper AskPDF arXiv

Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior. However, reasoning is not simple path imitation: rigidly following one demonstrated solution may overfit to surface forms and suppress the model's own reasoning distribution. We propose Rollout-Adaptive Supervised Fine-Tuning (RASFT), a policy-aware SFT framework that calibrates expert supervision according to problem-level solvability estimated from verified on-policy rollouts. For each problem, RASFT strengthens expert guidance when the current policy struggles, while relaxing rigid imitation and incorporating correct self-generated trajectories when the model already exhibits reliable reasoning behavior. To preserve useful reasoning priors, RASFT further introduces a clipped inverse ratio between the frozen reference model and the current policy to constrain excessive policy drift. Experiments across multiple models on six mathematical reasoning benchmarks and two code reasoning benchmarks show that RASFT achieves better overall performance than SFT, SFT variants, and representative RL methods. The code is available at https://github.com/zjd1sq/RASFT.

Momentum

Related topics

Latest papers 194