Fu-Dayuan / AgentRefine
(ICLR 2025) AgentRefine: Enhancing Agent Generalization through Refinement Tuning
☆11Updated last month
Alternatives and similar repositories for AgentRefine:
Users that are interested in AgentRefine are comparing it to the libraries listed below
- AgileGen: Empowering Agile-Based Generative Software Development through Human-AI Teamwork (accepted by ACM TOSEM)☆22Updated 4 months ago
- The official implementation of "LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented…☆23Updated last month
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆30Updated 10 months ago
- 最简易的R1结果在小模型上的复现，阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证，对于强推理能力，think思考过程性内容是AGI/ASI的核心。☆40Updated last month
- ☆94Updated 3 months ago
- OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation☆69Updated last week
- ☆56Updated 6 months ago
- Official implementation for "ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization"☆59Updated last month
- ☆102Updated 3 months ago
- autonomous agent with access to a tool library☆34Updated last month
- ☆47Updated last month
- connecting humans and agents☆80Updated 3 months ago
- ☆24Updated 2 months ago
- ☆55Updated this week
- HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model☆12Updated last month
- Official Implementation of "Reasoning Language Models: A Blueprint"☆54Updated last month
- Knowledge-Reasoning Synergy Reinforcement Learning.☆31Updated 3 weeks ago
- Automatic prompt optimization framework for multi-step agent tasks.☆28Updated 4 months ago
- ☆19Updated 3 months ago
- [EMNLP 2024] LongRAG: A Dual-perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering☆101Updated 2 months ago
- The source code and dataset mentioned in the paper Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmar…☆45Updated 4 months ago
- 超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of Dee…☆14Updated 3 weeks ago
- [ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"☆133Updated last month
- AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reaso…☆75Updated last week
- PGRAG☆47Updated 8 months ago
- ☆82Updated last month
- Parameter-Efficient Fine-Tuning for Foundation Models☆47Updated last month
- An open platform for enhancing the capability of LLMs in workflow orchestration.☆127Updated 2 weeks ago
- This is the code repo for our paper "Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts".☆28Updated 2 weeks ago
- ☆16Updated 5 months ago