arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.15481cs.AI
收藏

SkillFusion:面向大语言模型智能体的可靠多技能组合

SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents

Zhejiang University(浙江大学);Nanjing University(南京大学);Nanyang Technological University(南洋理工大学);City University of Hong Kong(香港城市大学)

Enhao Huang, Xinye Zhao, Yiming Li, Bingrun Yang, Nanjun Zhou, Chunshu Xia, Hongwei Yao, Zhan Qin

AI总结:

SkillFusion是一种离线编译器,通过类型化作用域约束等机制协调LLM智能体多技能的交互,在多基准测试中表现优异,成功率远超未解决的多技能加载方案。

摘要:

当大语言模型智能体同时加载独立编写的技能时,这些技能可能会产生不兼容的要求、相互冲突的偏好以及冗余的指令。我们提出SkillFusion,这是一种离线编译器,可将这些交互协调为可复用的合并技能。其核心思路是通过与源指令关联的类型化作用域约束,明确组合决策。类型-作用域门选择候选交互,选择性回退机制重新审视可能被结构剪枝遗漏的配对。分类器识别交互类型,对抗性验证器重新检查不确定的判断。解析器对硬冲突应用条件路由或显式优先级,对软冲突应用验证抽象,对冗余指令应用去重。与源关联的检查指导合成与压缩,元数据合成支持合并技能的发现。生成的产物保留相关脚本和资源,可在不同任务和执行器模型间复用。SkillFusion在所有三个智能体基准测试以及三个执行器模型的两个迁移基准测试中,在评估的非神谕方法中实现了最高的平均成功率。在测试的最大指令配置下,其成功率是未解决多技能加载方案的2.5倍以上,凸显出随着组合需求提升,协调的价值日益显著。代码将在评审流程结束后开源。

英文摘要:

Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM agent. We propose SkillFusion, an offline compiler that reconciles these interactions into a reusable merged skill. Its central idea is to make composition decisions explicit through typed, scoped constraints linked to their source directives. A type-scope gate selects candidate interactions, while selective fallback revisits pairs potentially missed by structural pruning. A classifier identifies interaction types, and an adversarial verifier re-examines uncertain judgments. The resolver applies conditional routing or explicit priorities to hard conflicts, verified abstraction to soft conflicts, and deduplication to redundant instructions. Source-linked checks guide synthesis and compression, and metadata synthesis supports discovery of the merged skill. The resulting artifact retains associated scripts and resources and can be reused across tasks and executor models. SkillFusion achieves the highest mean Success among evaluated non-oracle methods on all three agent benchmarks and on both transfer benchmarks across three executor models. At the largest tested instruction configurations, it achieves over 2.5 times the Success of unresolved multi-skill loading, highlighting the growing value of reconciliation as composition becomes more demanding. The code will be open-sourced after the review process concludes.

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。

↑