AtomSearch：面向 Agent 技能优化的证据锚定树搜索

View PDF HTML (experimental)

Abstract:Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judging each local edit only by its immediate score can discard useful intermediate states. We introduce AtomSearch, which keeps revision actions local while using subsequent skill states to guide search. Contrastive atomic editing links each primitive rule edit to failed and successful executions, a behavioral hypothesis, and an intended scope. Skill-State Tree Search (STS) evaluates short edit compositions and selectively retains them as executable states that can be revisited and extended. Outcome memory supplies later proposals with observed repair and regression statistics. We evaluate AtomSearch across four tasks and five target models. With deepseek-v4-flash, it exceeds SkillOpt on three of four tasks, including a 9.68-percentage-point gain on LiveMathematicianBench, and SkillOpt's final skills contain 2.3-19.7 times as many characters. In 67% of completed searches, the best validation state passes through an ancestor that was not highest-scoring at its depth. These results show how local rule edits can support the exploration of useful revision paths and yield compact skills, with additional offline evaluations used to explore alternative states.

Comments:	15 pages, 5 figures, 5 tables
Subjects:	Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2610.19951 [cs.CL]
	(or arXiv:2610.19951v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.19951 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jia Tong [view email]
[v1] Wed, 14 Oct 2026 10:33:30 UTC (244 KB)