ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

Resources of deep learning for mathematical reasoning (DL4MATH).

🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal reinforcement learning, and text-only reinforcement learning—to achieve faithful, concise, and self-reflective state-of-the-art performance in visual and textual reasoning.

[NeurIPS 2024] Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"

Small and Efficient Mathematical Reasoning LLMs

[ACL'24] Code and data of paper "When is Tree Search Useful for LLM Planning? It Depends on the Discriminator"

[EMNLP '23] Discriminator-Guided Chain-of-Thought Reasoning

Evaluation Code Repo for Paper "PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts"

[NeurIPS 2024] Code and Data Repo for Paper "Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning"

[ACL 2024 Findings] The official repo for "ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models".

🧠 Train your own DeepSeek-R1 style reasoning model on Mac! First MLX implementation of GRPO - the breakthrough technique behind R1's o1-matching performance. Build mathematical reasoning AI without expensive RLHF. Apple Silicon optimized. 🚀 A batteries‑included training & inference framework for **MLX**‑based language models on Apple Silicon.

The lecture notes for my discrete mathematics classes.

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

MathPrompter Implementation: This repository hosts an implementation based on the 'MathPrompter: Mathematical Reasoning Using Large Language Models' paper by Microsoft Research. The code replicates the methods discussed in the paper.

[AAAI 2025] Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical Problems

Fuzzy reasoning of Generalized Quantifiers (EMNLP 2024)

GSM8K-Consistency is a benchmark database for analyzing the consistency of Arithmetic Reasoning on GSM8K.

Bachelor thesis codebase: GRPO training for improving mathematical reasoning in small language models using reinforcement learning

This dataset aggregates carefully selected elementary-level math problems from various existing resources, providing an optimal mix for testing and enhancing math-solving chatbots for young learners.

We implement and benchmark various prompting techniques for LLMs (i.e. PAL, CoT, PoT, etc.) on a specialized math reasoning dataset (on elementary school grade).