Rerank agent skills by decomposed subtask, not by whole-task similarity (SkillReranker)

arXiv 2607.06283·medium signal

arXiv 2607.06283 attacks the problem that growing skill libraries make selection harder. SkillReranker performs semantic decomposition on both the task side and the skill side, builds a directed acyclic execution graph with intermediate task states as nodes and candidate skills as edges, then cross-encodes over candidates per task interval. On ALFWorld and ScienceWorld across three backbone LLMs it improved task performance while reducing both environment interaction steps and token consumption — a rare case where accuracy and cost move the same direction.