#Mathematical Reasoning

Articles (11)

• 🇺🇸 GRPO and Reflection Reward for Mathematical Reasoning in Large Language Models — 17/03/2026 [USA]

  arXiv:2603.14041v1 Announce Type: new Abstract: The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and rei...

  Related: #AI Research
• 🇺🇸 TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib? — 16/03/2026 [USA]

  arXiv:2603.12744v1 Announce Type: cross Abstract: Automated theorem proving (ATP) benchmarks largely consist of problems formalized in MathLib, so current ATP training and evaluation are heavily bias...

  Related: #AI Evaluation
• 🇺🇸 IndiMathBench: Autoformalizing Mathematical Reasoning Problems with a Human Touch — 12/03/2026 [USA]

  arXiv:2512.00997v2 Announce Type: replace Abstract: Reliable autoformalization remains challenging even in the era of large language models (LLMs). The scarcity of high-quality training data is a maj...

  Related: #Benchmark Development
• 🇺🇸 Deconstructing Multimodal Mathematical Reasoning: Towards a Unified Perception-Alignment-Reasoning Paradigm — 10/03/2026 [USA]

  arXiv:2603.08291v1 Announce Type: new Abstract: Multimodal Mathematical Reasoning (MMR) has recently attracted increasing attention for its capability to solve mathematical problems that involve both...

  Related: #AI Research
• 🇺🇸 VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMs — 09/03/2026 [USA]

  arXiv:2506.06727v4 Announce Type: replace Abstract: Large Multimodal Models have achieved remarkable progress in integrating vision and language, enabling strong performance across perception, reason...

  Related: #AI Benchmarking
• 🇺🇸 Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning — 06/03/2026 [USA]

  arXiv:2603.05120v1 Announce Type: new Abstract: Enhancing mathematical reasoning in Large Language Models typically demands massive datasets, yet data efficiency remains a critical bottleneck. While ...

  Related: #AI Education
• 🇺🇸 Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance — 27/02/2026 [USA]

  arXiv:2602.22583v1 Announce Type: new Abstract: Example-based guidance is widely used to improve mathematical reasoning at inference time, yet its effectiveness is highly unstable across problems and...

  Related: #Artificial Intelligence, #Strategy Optimization
• 🇺🇸 Our First Proof submissions — 20/02/2026 [USA]

  We share our AI model’s proof attempts for the First Proof math challenge, testing research-grade reasoning on expert-level problems.

  Related: #AI Research, #Scientific Advancement
• 🇺🇸 Chain of Thought in Order: Discovering Learning-Friendly Orders for Arithmetic — 19/02/2026 [USA]

  arXiv:2506.23875v3 Announce Type: replace-cross Abstract: The chain of thought, i.e., step-by-step reasoning, is one of the fundamental mechanisms of Transformers. While the design of intermediate re...

  Related: #Artificial Intelligence, #Transformer Models, #Chain of Thought, #Educational Technology
• 🇺🇸 AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning — 16/02/2026 [USA]

  arXiv:2505.23381v2 Announce Type: replace Abstract: Geometry problem solving presents distinctive challenges in artificial intelligence, requiring exceptional multimodal comprehension and rigorous ma...

  Related: #Artificial Intelligence, #Neuro-Symbolic Systems
• 🇺🇸 Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation — 29/01/2026 [USA]

  arXiv:2601.20614v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) offers a robust mechanism for enhancing mathematical reasoning in large models. However, we ident...

  Related: #Artificial Intelligence, #Technological Advancements