THUDM/AgentTuning
A method and open-source toolkit for tuning large language models to perform as generalized AI agents across multi-step real-world tasks.
Not currently ranked — collecting fresh signals.
star history
AgentTuning fine-tunes LLMs on interaction trajectories to imbue them with agent abilities such as multi-step reasoning, tool use, and task execution. The project provides the AgentInstruct dataset containing 1,866 curated interactions spanning 6 real-world task scenarios, along with the resulting AgentLM models (up to 70B parameters) released on HuggingFace. The approach uses ReAct-style reasoning traces and rigorous quality filtering to ensure both agent generalization and retained general language capabilities.
Frequently asked
- What is THUDM/AgentTuning?
- A method and open-source toolkit for tuning large language models to perform as generalized AI agents across multi-step real-world tasks.
- Is AgentTuning open source?
- Yes — THUDM/AgentTuning is an open-source project tracked on heatdrop.
- What language is AgentTuning written in?
- THUDM/AgentTuning is primarily written in Python.
- How popular is AgentTuning?
- THUDM/AgentTuning has 1.5k stars on GitHub.
- Where can I find AgentTuning?
- THUDM/AgentTuning is on GitHub at https://github.com/THUDM/AgentTuning.