arXiv 2609.32993 · cs.AI · 2026-09-26
X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization
Sitao Cheng, Xunjian Yin, Zhiyuan Sun, Yuxuan Li, Ruiwen Zhou, Xiangru Jian, Victor Zhong
University of Waterloo
在最新榜 #229 本站收录于 2026-10-21
一句话要点
X-Tree 像分词器一样从轨迹中提取可复用的子流程，把分层经验直接训练进智能体权重。
X-Tree tokenises recurring sub-procedures in agent trajectories and trains on that hierarchy, improving generalisation without LLM calls.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲490
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- Player-1: Learning to Play from Synthetic Experience ▲348
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。