acceptodds
Desk rejected at ICLR 2027

SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents

Desk rejected at ICLR 2027, so left out of the paper lists and the map.

Abstract

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 the Success of unresolved multi-skill loading, highlighting the growing value of reconciliation as composition becomes more demanding.

Primary area:
applications to computer vision, audio, language, and other modalities
Keywords:
LLM agents, agent skills, skill merging, agentic systems, multi-agent framework, constraint-based reasoning

Related papers

Discussion (0)

Sign in to comment.