hkust-nlp / CodeIOLinks
[ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
☆534Updated last month
Alternatives and similar repositories for CodeIO
Users that are interested in CodeIO are comparing it to the libraries listed below
Sorting:
- Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆545Updated 3 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆395Updated last month
- AN O1 REPLICATION FOR CODING☆336Updated 6 months ago
- ☆938Updated 4 months ago
- ☆569Updated 2 months ago
- ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning☆936Updated last month
- Scaling Deep Research via Reinforcement Learning in Real-world Environments.☆450Updated 2 months ago
- ReasonFlux Series - Open-Sourced LLM Family for Reasoning, Coding, Reward Modeling and Data Selection☆406Updated last week
- Large Reasoning Models☆804Updated 6 months ago
- ☆773Updated last month
- R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning☆561Updated 3 weeks ago
- LIMO: Less is More for Reasoning☆960Updated 2 months ago
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆713Updated 3 months ago
- Tina: Tiny Reasoning Models via LoRA☆258Updated 3 weeks ago
- [ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale☆251Updated 2 weeks ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆406Updated 2 weeks ago
- ☆478Updated 2 weeks ago
- Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi e…☆491Updated 3 months ago
- SkyRL-v0: Train Real-World Long-Horizon Agents via Reinforcement Learning☆422Updated this week
- ☆317Updated 9 months ago
- Scalable RL solution for advanced reasoning of language models☆1,615Updated 3 months ago
- LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA☆496Updated 5 months ago
- AWM: Agent Workflow Memory☆275Updated 4 months ago
- Seed-Coder is a family of lightweight open-source code LLMs comprising base, instruct and reasoning models, developed by ByteDance Seed.☆500Updated 2 weeks ago
- ☆789Updated last week
- Search-o1: Agentic Search-Enhanced Large Reasoning Models☆927Updated last month
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"☆149Updated last week
- A series of technical report on Slow Thinking with LLM☆699Updated 2 weeks ago
- Scaling Data for SWE-agents☆256Updated this week
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆240Updated 2 months ago