← Back to all news
arXiv AI By Jiazheng Sun, Boyu Yang, Binhao Yuan, Mingxuan Li, Xin Peng

Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents

Read the original on arXiv AI →

Trace2Tower is a transition‑aware EigenTrace framework that transforms raw execution traces of large language model agents into a robust skill hierarchy. By abstracting step‑level interactions into canonical events and constructing a unified graph based on semantic compatibility, transition dynamics, and outcome evidence, it isolates stable, success‑aligned behavioral modes through contrastive spectral decomposition. These modes populate a dynamic skill tower of action templates, procedural routines, and overarching task strategies, which are continuously refined via verifier‑guided feedback, achieving superior performance on ALFWorld and WebShop benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
3d ago

DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents

DynSTEER is a dynamic stage‑wise trajectory evaluation framework designed for large language model agents performing long‑horizon tasks. It segments rollouts into stages anchored by key actions, uses a path‑tolerant milestone graph to accommodate diverse valid strategies, and adaptively routes queries to multi‑tier judges while halting unrecoverable executions early. Experiments show it improves evaluation discriminability by 85.2% over native methods, separates all model pairs with statistical significance, and saves 34.51% of execution steps on failed rollouts.

By Zhichao Shi, Wenjie Zhang, Xuhui Jiang, Xiaojun Wu, Cehao Yang, Chengjin Xu, Jian Guo, Yuanzhuo Wang
llmsagents
More like this →
arXiv AI
Jun 6

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

arXiv:2603. 25158v5 Announce Type: replace Abstract: Large Language Model (LLM) agents increasingly rely on domain-specific skills, yet manually authoring such skills does not scale, and skills generated purely from parametric knowledge often miss critical operational pitfalls.

By Jingwei Ni, Yihao Liu, Xinpeng Liu, Yutao Sun, Mengyu Zhou, Pengyu Cheng, Dexin Wang, Erchao Zhao, Xiaoxi Jiang, Guanjun Jiang
llmsagents
More like this →