tool-learning 开源项目推荐（30 个）

xlang-ai /OpenAgents

[COLM 2024] OpenAgents：野外语言代理的开放平台

thinkwee /AgentsMeetRL

Awesome List for Agentic RL

codefuse-ai /codefuse-chatbot

一个智能助手，服务于整个软件开发生命周期，由多代理框架提供支持，与DevOps Toolkits，Code&Doc Repo RAG等一起工作。

microsoft /ToRA

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

FudanDISC /DISC-FinLLM

DISC-FinLLM，中文金融大语言模型（LLM），旨在为用户提供金融场景下专业、智能、全面的金融咨询服务。DISC-FinLLM，一款中国金融大型语言模型（LLM），旨在为用户提供专业、智能且全面的金融咨询服务，适用于金融场景。

codefuse-ai /CodeFuse-muAgent

由 KG Engine 驱动的创新智能体框架

quchangle1 /LLM-Tool-Survey

This is the repository for the Tool Learning survey.

yxf203 /Awesome-Efficient-Agents

Survey and paper list on efficiency-guided LLM agents (memory, tool use, planning).

THUNLP-MT /StableToolBench

A new tool learning benchmark aiming at well-balanced stability and reality, based on ToolBench.

mangopy /tool-retrieval-benchmark

Official code for ACL2025 "🔍 Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models"

vortezwohl /Autono

A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.

Reason-Wang /ToolGen

[ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"

mangopy /Confucius-tool-learning

Official Repo for AAAI 2024 paper "Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum"

luban-agi /Awesome-Tool-Learning

A curated list of papers and applications on tool learning.

quchangle1 /DRAFT

The implementation for ICLR 2025 Oral: From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions.

shizhl /Confucius

Official code for AAAI2023 paper`Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum`

zjunlp /TRICE

[NAACL 2024] Making Language Models Better Tool Learners with Execution Feedback

OSU-NLP-Group /Middleware

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (EMNLP'2024)

SqueezeAILab /Tool2Vec

Efficient and Scalable Estimation of Tool Representations in Vector Space

stormwther18 /HYSET

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction