Repository navigation
tool-learning
- Website
- Wikipedia
[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild
An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
An Innovative Agent Framework Driven by KG Engine
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, a Chinese financial large language model (LLM) designed to provide users with professional, intelligent, and comprehensive financial consulting services in financial scenarios.
This is the repository for the Tool Learning survey.
An Awesome List of Agentic Model trained with Reinforcement Learning
A ReAct-Based Highly Robust Autonomous Agent Framework.
Official code for ACL2025 "🔍 Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models"
A new tool learning benchmark aiming at well-balanced stability and reality, based on ToolBench.
[ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"
Official Repo for AAAI 2024 paper "Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum"
A curated list of papers and applications on tool learning.
Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
The implementation for ICLR 2025 Oral: From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions.
[NAACL 2024] Making Language Models Better Tool Learners with Execution Feedback
Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (EMNLP'2024)
Efficient and Scalable Estimation of Tool Representations in Vector Space
[COLING 2025] NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models
Official code for AAAI2023 paper`Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum`