hkust-nlp / CodeIOLinks
[ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
☆550Updated 4 months ago
Alternatives and similar repositories for CodeIO
Users that are interested in CodeIO are comparing it to the libraries listed below
Sorting:
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆602Updated 6 months ago
- AN O1 REPLICATION FOR CODING☆335Updated 9 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆443Updated 4 months ago
- A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.☆692Updated 2 months ago
- Large Reasoning Models☆805Updated 10 months ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆456Updated 3 months ago
- ☆1,273Updated 3 weeks ago
- [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents☆407Updated last week
- ☆963Updated 8 months ago
- ☆320Updated last year
- [NeurIPS 2025 Spotlight] ReasonFlux Series - ReasonFlux, ReasonFlux-PRM and ReasonFlux-Coder☆492Updated this week
- Scaling Deep Research via Reinforcement Learning in Real-world Environments.☆610Updated 5 months ago
- An Open-Source Large-Scale Reinforcement Learning Project for Search Agents☆440Updated last week
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆547Updated 2 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆906Updated this week
- Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"☆665Updated 2 months ago
- Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.☆432Updated 3 weeks ago
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"☆160Updated 3 months ago
- Tina: Tiny Reasoning Models via LoRA☆284Updated last week
- R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning☆639Updated last month
- Seed-Coder is a family of lightweight open-source code LLMs comprising base, instruct and reasoning models, developed by ByteDance Seed.☆552Updated 3 months ago
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆271Updated 7 months ago
- Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…☆409Updated 3 weeks ago
- [ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale☆263Updated 2 months ago
- ☆202Updated 2 weeks ago
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents☆406Updated 2 months ago
- 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]☆1,050Updated last month
- Implementation for OAgents: An Empirical Study of Building Effective Agents☆262Updated last month
- ☆293Updated 4 months ago
- Prompt-to-Leaderboard☆256Updated 4 months ago