| title | LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents |
|---|---|
| authors | Xiaoxuan Peng, Kaiqi Zhang, Xinyu Lu, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun |
| date | 2026-05-28 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.29559 |
| upvotes | 11 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. However, training such agents is currently bottlenecked by a reliance on scraped external repositories, which limits domain diversity, environment controllability, and the targeting of specific capability deficits. We introduce LiteCoder-Terminal-Gen, a zero-dependency synthesis pipeline that autonomously generates executable and verifiable terminal training environments directly from domain specifications. Using this framework, we construct two large-scale resources: LiteCoder-Terminal-SFT, comprising 11,255 expert trajectories across 10 domains, and LiteCoder-Terminal-RL, featuring 602 verifiable environments for trajectory-level preference optimization. Supervised fine-tuning of Qwen-family models on our SFT dataset yields agents that significantly outperform their base counterparts. Notably, our 32B variant achieves 29.06%, 18.54%, and 34.00% pass@1 on Terminal Bench 1.0, 2.0, and Pro, respectively. Furthermore, applying Direct Multi-turn Preference Optimization (DMPO) on our RL environments yields additional performance gains. These results systematically demonstrate that fully synthetic, executable environments offer a scalable and verifiable supervision signal for mastering complex, real-world command-line workflows. |
cite
@misc{peng2026litecoder,
title={LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents},
author={Xiaoxuan Peng and Kaiqi Zhang and Xinyu Lu and Boxi Cao and Yaojie Lu and Hongyu Lin and Xianpei Han and Le Sun},
year={2026},
eprint={2605.29559},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.29559}
}