# DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement

> 标题为英语

> 全文为英语

**Published:** 2026年9月22日
**Author:** Siyuan Liu (Fudan University, Meituan Longcat Team), Fan Yu (Fudan University, Meituan Longcat Team), Dongyu Ru (Meituan Longcat Team), Yizhu Liu (Meituan Longcat Team), Yifan Yang (Meituan Longcat Team), Xuezhi Cao (Meituan Longcat Team), Xunliang Cai (Meituan Longcat Team), Yixin Cao (Fudan University)
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/dense-distilling-agent-trajectories-into-evidence-grounded-shortcut-tree

Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to distill these traces into reusable feedback without post-hoc outcome labels, drawing on their evidence of local progress,…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2609.21423)

**标签：** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*