Latest AI for Mathematics Research Papers

The newest AI for Mathematics papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks AI for Mathematics so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Hammering with Vampire in Lean
  Jonas Bodingbauer, Laura Kovács · arXiv · Oct 29, 2026

  We present Vampire-Hammer, a hammer for the Lean interactive theorem prover that discharges goals using the Vampire automated theorem prover and reconstructs proofs checked by the Lean kernel. Vampire-Hammer uses the Lean-auto framework to …

• Timestral
  Adrien Petralia, Alexandre Gavaudan, Artjom Joosen, Etienne Goffinet et al. · arXiv · Oct 27, 2026

  We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and…

• M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents
  Hannes Ill, Rafi Al Attrach, Rajna Fani, Ahram Han et al. · arXiv · Oct 27, 2026

  Clinical research over electronic health records depends on derived variables whose definitions sit outside the schema, in item codes, time windows, missingness rules, and output-grain choices that change cohorts and downstream conclusions.…

• Learning to Look Beyond Screens: Transferable Visual Observation from GUI Grounding
  Ruilin Yao, Xinyu Qiu, Tianyu Zou, Yi Rong et al. · arXiv · Oct 27, 2026

  Visual perception is evolving from passive recognition toward active, task-oriented observation. We investigate GUI grounding as a scalable source of spatial supervision for learning observation behaviors that transfer beyond interfaces. We…

• Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean
  Per Kristian Lehre · arXiv · Oct 26, 2026

  LLMs now prove hard theorems in Lean. Can they also design algorithms and prove their correctness and efficiency? LLM-guided design of optimisation heuristics (such as AlphaEvolve) is purely empirical. Automated theorem provers with LLMs pr…

• CulturalRiddles: A Multicultural Benchmark of Riddles
  My Chiffon Nguyen, Tianyi Hu, Vinod Anbalagan, Henry Gagnier et al. · arXiv · Oct 21, 2026

  As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important. However, many benchmarks remain English-centric, with limited cultural coverage and a focus on factua…

• Benchmarking Arabic Dialects for Math Problems
  Noor Abo Mokh, Teresa Lynn, Nizar Habash, Ahmed Elshabrawy et al. · arXiv · Oct 20, 2026

  Mathematical reasoning remains underexplored for low-resource languages, including Dialectal Arabic. To bridge this gap, we introduce the DAR-MGSM (Dialectal Arabic Multilingual Grade School Math) Benchmark, the first manually curated bench…

• Kronecker Delta Rule for Long Context Linear Attention
  Anamaria-Roberta Hartl, Levente Zólyomi, Michael List, Günter Klambauer et al. · arXiv · Oct 19, 2026

  We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associati…

• MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning
  Jihao Huang, Guangjia Chai, Zhirui Chen, Lei Wang et al. · arXiv · Oct 16, 2026

  GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused. We introduce MGE-PO, centered on four-quadrant (4Q) advantage shaping that combines verified correc…

• Anatomical Review of Automated Mathematics: Verification, Understanding, and Proof Reuse. Distinguishing Formal Correctness from Conceptual Progress in AI-Driven Mathematical Research
  Syed Muntasir Mamun · Zenodo (CERN European Organ... · Oct 15, 2026

  This paper presents a detailed anatomical review of Bloch and Noguer i Alonso's (2026) framework for automated mathematics, which seeks to separate formal correctness, faithful formalisation, and mathematical understanding. The original wor…

• Beyond LLM Judge: Mechanical Verification for Agentic Autoformalization
  Anna Mei, Michael R. Douglas · arXiv · Oct 14, 2026

  We introduce a novel method for verifying Lean formalizations that goes beyond LLM-judged faithfulness. Unlike most verification methods, which rely on LLMs or trained models, our method combines LLM-based semantic review with mechanical nu…

• Scaling Multilingual Safety and Reasoning Evaluation through Reasoning-Guided Translation
  Zahraa Al Sahili, Ioannis Patras, Matthew Purver · arXiv · Oct 14, 2026

  Large language models (LLMs) are increasingly deployed across languages, yet their safety and reasoning capabilities remain predominantly evaluated in English. Translating existing benchmarks offers a scalable approach to multilingual evalu…

• Decoupling Exploration from Optimization in RLVR
  Saif Punjwani, Micah Goldblum · arXiv · Oct 7, 2026

  Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas abs…

• Translating Informal Proofs into Formal Proofs Using a Chain of States
  Ziyu Wang, Bowen Yang, Chenyi Li, Yuan Zhang et al. · CSIAM Transactions on Appli... · Oct 7, 2026

  We address the problem of translating informal mathematical proofs expressed in natural language into formal proofs in Lean 4 under a constrained computational budget. Our approach is grounded in two key insights. First, informal proofs ten…

• Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
  Bingxi Hou, Guochao Jiang, Guofeng Quan, Weiqing Li et al. · arXiv · Oct 6, 2026

  On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, comparing teacher and student predictions requires alignment at both sequence and vocabulary levels. In this paper, we e…

• SCOPE: Certified Theorem Proving with a Language Model as the Policy Planner
  Hanchao Zhou, Jialei Li · arXiv · Oct 6, 2026

  In proof assistants such as Lean, a generated proof must pass machine compilation checks, so evaluation needs no human scoring. Direct generation fails on multi-step numeric propositions: a proof is valid only if every content integer is co…

• IdeaLens: Detecting AI Ideas in Long-form Writing
  Rishanth Rajendhran, Minjoon Choi, Jenna Russell, Ramya Namuduri et al. · arXiv · Oct 5, 2026

  While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce IdeaLens, a detector that identifies whether a document's ideas came fr…

• Preserving Mathematical Reasoning in Compressed Diffusion Language Models via Trajectory-Aware Low-Rank Approximation
  Tian Liang, Zishan Shao, Yiran Chen · arXiv · Oct 2, 2026

  Diffusion language model (dLLM) compression faces a known challenge because calibration is typically performed on clean, fully visible activations, whereas inference traverses partially masked intermediate states. For low-rank compression, …

• CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning
  Yafei Zhang, Songshuo Lu, Sicong Liao, Zhi Chen et al. · arXiv · Oct 1, 2026

  Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-training, with substantial gains in mathematical reasoning and code generation. In practical systems, however, policy updates a…

• Cogentic: Multi-Agent Orchestration for Automated Proof Discovery
  Yang Cai, Vineet Gupta, Yanchen Jiang, Christopher Liaw et al. · arXiv · Sep 30, 2026

  We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for ope…

• Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning
  Zhixu Silvia Tao · arXiv · Sep 23, 2026

  Reordering a set of mathematical rules without changing its meaning should preserve the correct answer, but must a model's internal representations stay invariant too? We investigate this question using synthetic multi-step function-composi…

• When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment
  Jie Zhang, Jingxiao Yang, Zhehao Huang, Yuhang Liu et al. · arXiv · Sep 23, 2026

  Reinforcement learning with verifiable rewards (RLVR) supervises mathematical reasoning through final-answer correctness, but provides little guidance on individual tokens. On-policy distillation (OPD) supplies dense feedback on student-gen…

• Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
  Wenkang Qin, Yukun Zhou, Noah Shen, Jisong Cai et al. · arXiv · Sep 21, 2026

  Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a data-dr…

• Explainable AI for Mathematics: Proofs as Code with Knowledge Graph and Domain Ontology Support
  Oli Ataeva, Khalov A., Tuchkova N. · Mathematics & AI · May 22, 2026

  We investigate whether structured knowledge retrieval from a mathematical library's dependency graph can improve neural theorem proving at inference time while maintaining explainability of the retrieved context. Through a controlled ablati…