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

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
ISM:Self-Improving Strategy Memory for Continual Mathematical Reasoning
Jun 30, 2026Prakhar Dixit, Tim OatesContinual Learning for LLMs Memory-Augmented Language Models
Department of Computer Science, University of Maryland, Baltimore County, Baltimore, Maryland, USA
Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning
Jun 29, 2026Sangmook Lee, Minbeom Kim, Jeonghye Kim +3LLM Evaluation Reasoning Diversity
Seoul National University · KAIST
The Ramanujan Challenge For AI
Jun 27, 2026Michael Shalyt, Rotem Kalisch, Carsten Schneider +7Mathematical Reasoning Benchmarks LLM Mathematical Reasoning
1Ramanujan Machine Group, Technion, Haifa, Israel. · 2Research Institute for Symbolic Computation, Johannes Kepler Universität Linz, Linz, Austria. · Department of Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium. +1
Self-Supervised Theorem Discovery in a Formal Axiomatic System
Jun 27, 2026Kazuki Ota, Takayuki Osa, Tatsuya HaradaAutomated Theorem Proving Knowledge Augmentation for Language Models
The University of Tokyo, Japan · RIKEN AIP, Japan
Riazi-8B: An Urdu Large Language Model for Mathematical Reasoning
Jun 24, 2026Azher Ali, Ibtsam Haider, Raja Khurram Shahzad +2Numerical Reasoning in Language Models LLM Fine-Tuning
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad, Pakistan · Department of Communication, Quality Management and Information Systems, Mid Sweden University, Ostersund, Sweden
Cliff Tokens: Analyzing Failure Trigger Tokens in LLM Mathematical Reasoning
Jun 24, 2026Jaeyong Ko, Jinu Lee, Pilsung Kang +1Numerical Reasoning in Language Models LLM Reliability
Seoul National University · Boston University
Human vs Machine Mathematical Difficulty on Project Euler: An Experimental Analysis
Jun 20, 2026David Holmes, Johannes SchmittMathematical Reasoning Benchmarks Language Model Scaling Laws
Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation
Jun 17, 2026Luca Zhou, Sajel Shah, Emanuele Rodolà +1Mathematical Reasoning Benchmarks LLM Evaluation
1Sapienza University of Rome · 2Not Diamond · 3Paradigma
First Proof Second Batch
Jun 16, 2026Mohammed Abouzaid, Nikhil Srivastava, Rachel Ward +1Mathematical Reasoning Benchmarks LLM Mathematical Reasoning
Stanford University · University of California, Berkeley · University of Texas at Austin +1
MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning
Jun 16, 2026Wanshi Xu, Haokun Zhao, Haidong Yuan +2Multimodal Reasoning Multimodal Reward Modeling
School of ECE, Peking University · College of Computer Science and Artificial Intelligence, Fudan University · School of Software and Microelectronics, Peking University +1
Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics
Jun 16, 2026Xiyu Zhai, Xinyi Chen, Yiping Wang +3Automated Theorem Proving Lean Theorem Proving
University of Washington · University of Innsbruck
The Discrete-Log Clock: How a Transformer Learns Modular Multiplication
Jun 16, 2026Huu Danh NguyenTransformer Interpretability Frequency-Domain Feature Learning
Stanford University
Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty
Jun 15, 2026Baishali Chaudhury, Mengdie Flora Wang, Hyunji Hayley Park +3Reasoning Consistency in Language Models LLM Reliability
AWS Generative AI Innovation Center
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
Jun 15, 2026Haolong Qian, Xianliang Yang, Yinuo ma +6CoT Distillation Language Model Distillation
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Microsoft Research Asia, Microsoft, Beijing, China · Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology, Shenzhen, China +1
Theorem-Grounded Execution Ontologies for Interpretable Machine Reasoning
Jun 14, 2026Raghu AnantharangacharInterpretable ML Formal Verification
Independent Researcher · Bangalore, India
Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning
Jun 14, 2026Ji Feng, Zhouxing ShiLLM Answer Verification Lean Theorem Proving
University of California, Riverside
Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs
Jun 13, 2026Jierui Zhang, Siyuan Tan, Xinhang Li +8Mathematical Reasoning Benchmarks LLM Evaluation
School of Computer Science Beijing University of Posts and Telecommunications Beijing, China · Graduate College for Engineers Beijing University of Posts and Telecommunications Beijing, China · School of Mathematical Sciences Fudan University Shanghai, China +6
Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation
Jun 12, 2026Arnesh Banerjee, Ayushi BhattacharjeeMathematical Reasoning Benchmarks LLM Auditing
Dept. of CSE (Data Science) Heritage Institute of Technology Kolkata, India
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
Jun 11, 2026Jiacheng Chen, Xinyu Zhang, Shunkai Zhang +20Automated Theorem Proving Inference-Time Scaling
MiniMax · The Chinese University of Hong Kong · Fudan University +2
Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning
Jun 10, 2026Kai Liu, Peijie Dong, Xinchen Xie +5RL for Language Model Reasoning LLM Inference Acceleration
Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University · Hong Kong University of Science and Technology (Guangzhou) · Shanghai AI Laboratory
Evaluating Research-Level Math Proofs via Strict Step-Level Verification
Jun 9, 2026Yifeng SunLLM Answer Verification Automated Theorem Proving
Independent Researcher
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization
Jun 9, 2026Xukun Zhu, Hang Yu, Peng Di +1RL for Language Model Reasoning Group Relative Policy Optimization
Zhejiang University · Ant Group
ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics
Jun 9, 2026Shunkai Zhang, Haoran Zhang, Yun Luo +15Mathematical Reasoning Benchmarks Benchmark Design
2Peking University · 1Shanghai AI Laboratory · 3Shanghai Jiao Tong University +2
KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty
Jun 9, 2026Sanghee Park, Geewook Kim, Kee-Eung KimVLM Evaluation Mathematical Reasoning Benchmarks
NAVER Cloud AI · KAIST AI
Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models
Jun 8, 2026Xinyue Liang, Yizhe Yang, Yu Bai +3Reasoning Diversity RL for Language Model Reasoning
School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China
Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery
Jun 7, 2026Syed Rifat Raiyan, Mohsinul Kabir, Hasan Mahmud +2Mathematical Reasoning Benchmarks Automated Theorem Proving
Systems and Software Lab (SSL), Department of Computer Science and Engineering, Islamic University of Technology, Gazipur, Bangladesh · Department of Computer Science, University of Manchester, Manchester, United Kingdom
A Comprehensive Anatomy of Human and DeepSeek-R1 LLM Mathematical Reasoning
Jun 5, 2026Yuxiang Chen, Jun WangCoT Reasoning Structured Reasoning
UCL Centre for Artificial Intelligence
From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning
Jun 5, 2026Yuhang Zhou, Yixin Cao, Guangnan YeProcess Reward Models RL for Language Model Reasoning
Fudan University · Shanghai Innovation Institute

Jul 2, 2026, cs.CLJ/K move · Enter open · S save

TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B

Baran Bingol, Bahaeddin Turkoglu

Department of Artificial Intelligence and Data Engineering Faculty of Engineering Ankara University Ankara, Türkiye

LLM Fine-Tuning LLM Mathematical Reasoning LLM Reasoning

Open paper AskPDF arXiv

This paper presents TUDUM (Türkçe Düşünen Üretken Model), a project pipeline for adapting a Qwen-family 27B thinking model toward Turkish reasoning. The central problem is not only to answer Turkish prompts in Turkish, but to make the explicit reasoning trace itself Turkish. A thinking model may translate a Turkish prompt into an English-centered internal or visible scratchpad, solve the problem mostly in English, and only localize the final answer. TUDUM instead treats the generated <think>...</think> block as a trainable behavior. The pipeline starts from the project base checkpoint unsloth/Qwen3.5-27B, applies supervised fine-tuning (SFT) on 15,991 Turkish reasoning examples using LoRA adapters, and then applies GRPO-family reinforcement learning on a proxy-filtered Turkish mathematics environment. The results are mixed. SFT made the model shorter and more consistently Turkish in its reasoning behavior, with large reductions in average response length and thinking exhaustion, but reduced benchmark accuracy. RL recovered some mathematical performance, especially AIME24 at the best early checkpoint, yet did not uniformly improve all benchmarks and did not exceed the base model on the reported Macro-6 average. The contribution is therefore best framed as a technically honest Turkish-thinking reasoning pipeline and evaluation, not as a claim of state-of-the-art Turkish reasoning. The released step-50 model is publicly available.

Momentum

Related topics

Latest papers 194