Open-source alternatives to GPT4Tools

Code for paper "CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets"

🚀 VLM-Powered Agent for Intelligent Tool Orchestration | 🔧 Open-source Framework for Multi-modal AI

``` STE/ ├─ toolmetadata/: tool related metadata ├─ prompts/: full prompts used ├─ savedresults/: prediction results in json ├─ {, FT, ICL}.json: results for baseline model, tool-enhanced w/ fine-tuning, tool-enhanced with ICL ├─ CLround.json: continual learning (each round) ├─ main.py: main…

Chenyu Wang, Weixin Luo, Qianyu Chen, Haonan Mai, Jindi Guo, Sixun Dong, Xiaohua (Michael) Xuan, Zhengxin Li, Lin Ma, Shenghua Gao.

This is the official implementation of paper Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning, where we present Nemotron-Research-Tool-N1, a family of tool-using reasoning language models. These models are trained with an R1-style reinforcement learning…

ICLR 2025 Tool-Planner: Task Planning with Clusters across Multiple Tools

Large Language Models (LLMs) have exhibited significant potential in performing diverse tasks, including the ability to call functions or use external tools to enhance their performance. While current research on function calling by LLMs primarily focuses on single-turn interactions, this paper…

We release here the code for most of the main experiments in paper CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models, including the code of our framework and various baselines. We also release two new datasets: Creation Challenge and Tool Transfer…

🤗 Model | 📊 Dataset | 📖 Paper

🛠️🤖 From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs ByteDance Seed

Code for paper "Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation", presented at ICML2025.

ICLR 2026 Agentic Reinforced Policy Optimization (ARPO)

🔧✨Tool-Star: Empowering Multi-Tool Collaborative Web Agent via Reinforcement Learning

SPORT introduces an online self-exploration loop that enables multimodal agents to self-improve via AI-generated tasks and LLM-verified preference tuning without human annotations.

ToolAlpaca is a framework designed for learning generalized tool-use abilities in compact language models with minimal human supervision. It addresses the challenge of tool learning by generating a tool-use corpus via a multi-agent simulation environment, providing 3.9k tool-use instances from…

Inspired by the human ability to adaptively select tools, we introduce AutoTIR, a reinforcement learning framework that enables LLMs to autonomously decide whether and which tool to invoke during the reasoning process, rather than following static tool-use strategies. AutoTIR leverages a hybrid…

PLAY2PROMPT - Interactive Tool-use Example Generation & Tool Documentation Optimization Implementation for the paper PLAY2PROMPT.

Weizhou Shen 1 , Chenliang Li 2 , Hongzhan Chen 1 , Ming Yan 2 , Xiaojun Quan 1 , Hehong Chen 2 , Ji Zhang 2 , Fei Huang 2 shenwzh3@mail2.sysu.edu.cn, quanxj3@mail.sysu.edu.cn, ym119608@alibaba-inc.com 1 Sun Yat-sen University 2 Alibaba Group *Corresponding authors

Data Release • Web Demo • Tool Eval • Paper • Citation

https://arxiv.org/abs/2506.01056

The GAIA game is over, and Alita is the final answer.

This repository contains the code and benchmark (ToolQA-D) for our research paper titled "Learning Evolving Tools for Large Language Models", which has been accepted at ICLR 2025.