SkillShift-Bench is a new benchmark that evaluates web agents’ skill learning under controlled open-environment shifts, including Contextual, Perceptual, and Execution shifts across three self-hosted web systems. It measures task success, interaction cost, skill use, and skill failure, revealing that skill robustness degrades systematically—especially under Execution Shift. The benchmark also frames shifted skill execution as a nonstationary local executability problem, offering a dynamic-regret analysis and a test-time adaptation method to improve skill execution without relearning.
arXiv:2604.13318v2 Announce Type: replace Abstract: Autonomous web agents powered by large language models (LLMs) remain brittle on long-horizon browser workflows. A key bottleneck is a grounding gap...
arXiv:2610.35823v1 Announce Type: new Abstract: Browser agents do not just need more practice. They need to practice the right things. We introduce MiniWeb, a realistic miniature of the web comprisin...
arXiv:2606. 04391v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks.
arXiv:2608. 06474v1 Announce Type: new Abstract: Large language models increasingly generate complete websites from natural-language descriptions, and reinforcement learning has become a central approach to closing their remaining functional gap.
arXiv:2604. 08377v2 Announce Type: replace Abstract: Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment.
SCAFFOLD is a self‑improving framework for visual web agents that automatically induces parametric, executable skills from successful trajectories and organizes them into a recursively composed hierarchy. It compresses the skill library using a minimum‑description‑length criterion and behavioral equivalence checks, and periodically distills these skills back into model weights to internalize the abstractions. Experiments on WebArena, VisualWebArena, and Online‑Mind2Web show that SCAFFOLD raises success rates by 11.1–17.2 absolute points over the best skill‑augmented baseline and continues to improve across five self‑improvement iterations without collapsing the library.
arXiv:2605. 28390v2 Announce Type: replace Abstract: Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems.
arXiv:2609.35814v1 Announce Type: cross Abstract: As browser-use agents improve, benchmarks keep pace by collecting new tasks, websites, and applications, often making tasks longer or more novel. Thi...
The paper surveys the evolving field of agent skill evaluation and evolution, emphasizing the shift from isolated skill creation to automated, evaluation-driven development. It categorizes skill evolution into four paradigms—execution feedback, trajectory distillation, compression, and reinforcement learning—and analyzes six skill-centric benchmark categories to highlight gaps and trade-offs. The authors outline open research directions for building generalizable, efficient, and verifiably safe skill ecosystems.
arXiv:2608.21898v1 Announce Type: new Abstract: Web agents promise to automate complex digital workflows, but their training remains limited by synthetic environments that look plausible while hiding...
arXiv:2606. 01311v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks.
arXiv:2606. 17645v1 Announce Type: new Abstract: Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action.