遇见数据集

References for Learning CLI Agents with Structured Action Credit under Selective Observation

收藏
Zenodo2026-09-07 更新2026-10-01 收录
官方服务:

资源简介:

Haoyang Su and Ying Wen. Learning CLI Agents with Structured Action Credit under Selective Observation. arXiv:2605.08013, 2026. https://arxiv.org/abs/2605.08013 This deposit contains the reference list of the paper. Related work includes GiGPO (Feng et al., 2025; arXiv:2505.10978), HGPO (He et al., 2026; arXiv:2602.22817), GRPO (Shao et al., 2024; arXiv:2402.03300), turn-level credit assignment (arXiv:2505.11821), SWE-agent (arXiv:2405.15793), OpenHands (arXiv:2407.16741), Terminal-Bench (arXiv:2601.11868), and SWE-bench (arXiv:2310.06770). Code: https://github.com/Hoyant-Su/Agentic-RL-A3Data: https://huggingface.co/datasets/Hoyant-Su/ShellOps

提供机构:
Zenodo
创建时间:
2026-09-07
二维码
社区交流群
二维码
科研交流群
商业服务