Skip to content

WangHanLinHenry/STeCa

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

10 Commits
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

STeCa

This repository contains the code for the paper "STeCa: Step-level Trajectory Calibration for LLM Agent Learning"

In this work, We propose Step-Level Trajectory Calibration (STeCa), a novel framework for improving LLM agents. Specifically, STeCa identifies suboptimal actions through a step-level reward comparison during explorations. It constructs calibrated trajectories using LLM-driven reflection, enabling agents to learn from improved decision-making processes. These calibrated trajectories, together with successful trajectory data, are utilized for reinforced training.

⛏️ Usage

Coming soon...

πŸ“‚ Released Dataset

Please refer to dataset/ for the released data of ALFWorld and VirtualHome.

πŸ“– Citation

If you find this repo helpful, please cite our paper:

@article{wang2025steca,
  title={STeCa: Step-level Trajectory Calibration for LLM Agent Learning},
  author={Wang, Hanlin and Wang, Jian and Leong, Chak Tou and Li, Wenjie},
  journal={arXiv preprint arXiv:2502.14276},
  year={2025}
}

πŸ™ Acknowledgments

This codebase is built from ETO and IPR.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published