-
slime Public
Forked from THUDM/slimeslime is a LLM post-training framework aiming at scaling RL.
Python Apache License 2.0 UpdatedJun 20, 2025 -
-
TreeRL Public
Forked from THUDM/TreeRLTreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25
Python Apache License 2.0 UpdatedJun 16, 2025 -
SWE-bench-Live Public
Forked from microsoft/SWE-bench-Live🚀 SWE-bench Goes Live!
Python MIT License UpdatedMay 30, 2025 -
-
RedTeamCUA Public
Forked from OSU-NLP-Group/RedTeamCUARedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Python Apache License 2.0 UpdatedMay 29, 2025 -
EvoAgentX Public
Forked from EvoAgentX/EvoAgentX🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
Python Other UpdatedMay 28, 2025 -
SynLogic Public
Forked from MiniMax-AI/SynLogicThe official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
Python MIT License UpdatedMay 28, 2025 -
deer-flow Public
Forked from bytedance/deer-flowDeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
TypeScript MIT License UpdatedMay 28, 2025 -
agent-distillation Public
Forked from Nardien/agent-distillationPython Apache License 2.0 UpdatedMay 26, 2025 -
One-RL-to-See-Them-All Public
Forked from MiniMax-AI/One-RL-to-See-Them-AllOne RL to See Them All: Visual Triple Unified Reinforcement Learning
MIT License UpdatedMay 25, 2025 -
InternBootcamp Public
Forked from InternLM/InternBootcampPython Apache License 2.0 UpdatedMay 23, 2025 -
-
-
WebOrganizer Public
Forked from CodeCreator/WebOrganizerOrganize the Web: Constructing Domains Enhances Pre-Training Data Curation
Jupyter Notebook Apache License 2.0 UpdatedMay 2, 2025 -
-
MM-EUREKA Public
Forked from ModalMinds/MM-EUREKAMM-EUREKA: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Python Apache License 2.0 UpdatedMar 8, 2025 -
AppAgentX Public
Forked from Westlake-AGI-Lab/AppAgentXOfficial implementation of AppAgentX: Evolving GUI Agents as Proficient Smartphone Users
Python UpdatedMar 6, 2025 -
-
kodcode Public
Forked from KodCode-AI/kodcodeGenerate diverse coding questions and verifiable solutions - all in one framework
Python Apache License 2.0 UpdatedMar 5, 2025 -
RAGEN Public
Forked from RAGEN-AI/RAGENRAGEN is the first open-source reproduction of DeepSeek-R1 on AGENT training.
Python Apache License 2.0 UpdatedFeb 6, 2025 -
demystify-long-cot Public
Forked from eddycmu/demystify-long-cotPython MIT License UpdatedFeb 5, 2025 -
-
WorfBench Public
Forked from zjunlp/WorfBench[ICLR 2025] Benchmarking Agentic Workflow Generation
Python MIT License UpdatedNov 26, 2024 -
VinePPO Public
Forked from McGill-NLP/VinePPOCode for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"
Python MIT License UpdatedOct 3, 2024 -
show-me Public
Forked from mrm8488/show-meA visual and transparent alternative to open-source ChatGPT O1
Python UpdatedSep 26, 2024 -
ell Public
Forked from MadcowD/ellA language model programming library.
Python MIT License UpdatedSep 23, 2024 -
LeanRL Public
Forked from pytorch-labs/LeanRLLeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
Python Other UpdatedSep 20, 2024 -
-
{{ message }}