用于自适应智能体技能检索的任务分解引导重排序
Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval
AI总结：
针对技能库规模增长带来的技能选择挑战，提出SkillReranker框架，通过任务和技能语义分解构建执行图，利用交叉编码器评分，在多场景实验中有效提升任务性能、减少交互步骤并降低令牌消耗。
摘要：
技能使用可显著提升现代智能体系统完成复杂任务的能力。然而，技能库规模的增长使准确的技能选择愈发具有挑战性。在现实场景中，特定任务需求与多个语义相似的候选技能间常出现模糊语义匹配。此外，现有方法在选择最优目标技能集时往往忽略任务难度和技能适用性的动态影响。为解决这些问题，我们提出SkillReranker，一种用于自适应技能选择的推理时重排序框架。具体而言，我们首先在任务和技能方面进行语义分解，得到信息丰富的子任务、执行状态描述以及表征每个技能功能的过渡状态描述。然后用这些描述构建有向无环执行图，将中间任务状态建模为节点，候选技能建模为边，从而建立结构化的任务-技能对应关系。在此基础上，SkillReranker确定每个状态节点是否满足分割条件以识别子任务区间。对于每个任务区间，我们使用交叉编码器对候选技能进行综合评分，选择最合适的技能形成最终目标技能集进行实验。在ALFWorld和ScienceWorld上使用三个主干语言模型的实验表明，与现有技能选择基线相比，SkillReranker有效提高了任务性能，减少了环境交互步骤，并降低了令牌消耗。
英文摘要：
Skill usage can significantly enhance the ability of modern agent systems to complete complex tasks. However, the growing scale of skill libraries makes accurate skill selection increasingly challenging. In real-world scenarios, ambiguous semantic matching often arises between a specific task requirement and multiple generic yet semantically similar candidate skills. Moreover, existing methods tend to overlook the dynamic influence of task difficulty and skill applicability when selecting the optimal target skill set. To address these issues, we propose SkillReranker, an inference-time reranking framework for adaptive skill selection. Specifically, we first perform semantic decomposition on both the task and skill sides, yielding informative subtask and execution-state descriptions as well as transition-state descriptions that characterize each skill's functionality. These descriptions are then used to construct a directed acyclic execution graph, where intermediate task states are modeled as nodes and candidate skills as edges, thereby establishing a structured task-skill correspondence. On this basis, SkillReranker determines whether each state node satisfies the split condition to identify subtask intervals. For each task interval, we employ a cross-encoder to perform comprehensive scoring over candidate skills and select the most suitable ones to form the final target skill set. Experiments on ALFWorld and ScienceWorld with three backbone LLMs show that SkillReranker effectively improves task performance, reduces environment interaction steps, and lowers token consumption compared with existing skill selection baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
