| ThoughtSource: A central hub for large language model reasoning data | Jan 27, 2023 | Language ModelingLanguage Modelling | CodeCode Available | 3 |
| Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks | Nov 22, 2022 | Math | CodeCode Available | 3 |
| PAL: Program-aided Language Models | Nov 18, 2022 | Arithmetic ReasoningGSM8K | CodeCode Available | 3 |
| SymForce: Symbolic Computation and Code Generation for Robotics | Apr 17, 2022 | Code GenerationMath | CodeCode Available | 3 |
| Training Verifiers to Solve Math Word Problems | Oct 27, 2021 | GSM8KMath | CodeCode Available | 3 |
| SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning | Jun 30, 2025 | MathMulti-agent Reinforcement Learning | CodeCode Available | 2 |
| OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling | Jun 25, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning | Jun 23, 2025 | GPULarge Language Model | CodeCode Available | 2 |
| Essential-Web v1.0: 24T tokens of organized web data | Jun 17, 2025 | Math | CodeCode Available | 2 |
| TreeRL: LLM Reinforcement Learning with On-Policy Tree Search | Jun 13, 2025 | Mathreinforcement-learning | CodeCode Available | 2 |
| Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning | Jun 11, 2025 | Image CaptioningMath | CodeCode Available | 2 |
| AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions | Jun 10, 2025 | Math | CodeCode Available | 2 |
| Play to Generalize: Learning to Reason Through Game Play | Jun 9, 2025 | Domain GeneralizationMath | CodeCode Available | 2 |
| MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning | Jun 5, 2025 | MathMathematical Reasoning | CodeCode Available | 2 |
| The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning | Jun 2, 2025 | MathMathematical Reasoning | CodeCode Available | 2 |
| Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO | May 28, 2025 | MathReinforcement Learning (RL) | CodeCode Available | 2 |
| Reinforcing General Reasoning without Verifiers | May 27, 2025 | MathMathematical Reasoning | CodeCode Available | 2 |
| R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing | May 27, 2025 | Math | CodeCode Available | 2 |
| MAS-Zero: Designing Multi-Agent Systems with Zero Supervision | May 26, 2025 | MathProblem Decomposition | CodeCode Available | 2 |
| WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning | May 22, 2025 | MathReinforcement Learning (RL) | CodeCode Available | 2 |
| Meta-Design Matters: A Self-Design Multi-Agent System | May 21, 2025 | MathProblem Decomposition | CodeCode Available | 2 |
| RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning | May 21, 2025 | MathMathematical Reasoning | CodeCode Available | 2 |
| AdaptThink: Reasoning Models Can Learn When to Think | May 19, 2025 | Math | CodeCode Available | 2 |
| Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space | May 19, 2025 | GSM8KMath | CodeCode Available | 2 |
| Synthetic Data RL: Task Definition Is All You Need | May 18, 2025 | AllGSM8K | CodeCode Available | 2 |
