ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
This addresses the issue of reusable skill acquisition for multimodal web agents, offering a novel approach to skill repair and verification.
The paper tackles the problem of brittle and hard-to-repair skills in multimodal GUI agents by introducing ContractSkill, a framework that converts draft skills into contracted artifacts with explicit specifications, improving self-generated skill success rates from 9.4% to 28.1% on VisualWebArena and from 66.5% to 77.5% on MiniWoB.
Despite rapid progress in multimodal GUI agents, reusable skill acquisition remains difficult because on-demand generated skills often leave action semantics, state assumptions, and success criteria implicit. This makes them brittle to execution errors, hard to verify, and difficult to repair. We present ContractSkill, a framework that converts a draft skill into a contracted executable artifact with explicit preconditions, step specifications, postconditions, recovery rules, and termination checks. This representation enables deterministic verification, step-level fault localization, and minimal patch-based repair, turning skill refinement into localized editing rather than full regeneration. Experiments on VisualWebArena and MiniWoB with GLM-4.6V and Qwen3.5-Plus show that ContractSkill improves self-generated skills from 9.4% and 10.9% to 28.1% and 37.5% on VisualWebArena, and from 66.5% and 60.5% to 77.5% and 81.0% on MiniWoB. Repaired artifacts also transfer across models, improving the target model's self-generated-skill baseline by up to 47.8 points and 12.8 points on the two benchmarks, respectively. These results suggest that agent skills are better treated as explicit procedural artifacts that can be verified, repaired, and shared across models.