SGDR enables stepwise skill reuse in web agents via sliding-window extraction, dual text-code representations, and state-grounded retrieval, delivering roughly 10% relative gains over baselines on WebArena.
ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottleneck is not only skill generation quality, but the fact that web skills remain implicit and therefore cannot be checked or locally repaired. To address this, we present ContractSkill, a framework that converts a draft skill into an executable artifact with explicit procedural structure, enabling deterministic verifica tion, fault localization, and minimal local repair. This turns skill refinement from full rewriting into localized editing of a single skill artifact. Experiments on VisualWebArena show that Contract Skill is effective in realistic web environments, while MiniWoB provides a controlled test of the mechanism behind the gain. Under matched transfer layers, repaired artifacts also remain reusable after removing the source model from the loop, providing evi dence of portability within the same benchmark family rather than full-benchmark generalization. These results suggest that the central challenge is not merely generating skills, but mak ing them explicit, executable, and repairable. Code is available at https://github.com/underfitting-lu/contractskill.git.
fields
cs.AI 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
Skim profiles website patterns offline to enable fast-path speculative execution for web agents, cutting median cost by 1.9x and latency by 33.4% with no accuracy loss on benchmarks.
SkillMigrator reduces LLM-action counts by 8-10% on WebArena and Mind2Web by transferring web skills via layout-matched transferable interaction patterns.
Catalogs ten patterns and synthesizes a four-layer reference architecture for skill harnessing in LLM agents, evaluated via cross-instantiation on eight systems.
citing papers explorer
-
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
SGDR enables stepwise skill reuse in web agents via sliding-window extraction, dual text-code representations, and state-grounded retrieval, delivering roughly 10% relative gains over baselines on WebArena.
-
Skim: Speculative Execution for Fast and Efficient Web Agents
Skim profiles website patterns offline to enable fast-path speculative execution for web agents, cutting median cost by 1.9x and latency by 33.4% with no accuracy loss on benchmarks.
-
Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
SkillMigrator reduces LLM-action counts by 8-10% on WebArena and Mind2Web by transferring web skills via layout-matched transferable interaction patterns.
-
Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents
Catalogs ten patterns and synthesizes a four-layer reference architecture for skill harnessing in LLM agents, evaluated via cross-instantiation on eight systems.