LATIDIA · Ciberseguridad

AgentHeal: Evaluating Goal-Preserving Resource Recovery of Web Agents under Access Barriers

arXiv: 2610.39234v1Tipo de anuncio: nuevo Resumen: Los agentes del modelo de lenguaje grande (LLM) han demostrado una gran capacidad para automatizar tareas complejas de búsqueda de información y transacciones en la web abierta. Sin embargo,

La noticia

arXiv:2610.39234v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capabilities in automating complex information-seeking and transactional tasks across the open web. However, their real-world reliability remains limited by access barriers, such as dead links, authentication walls, rate limits, and anti-scraping defenses. These barriers block the primary execution path, causing agents to abort prematurely, loop indefinitely, or quietly compromise the user's original constraints. Existing evaluations either implicitly assume that target resources are freely accessible or focus on transient perturbations that simple retries can resolve, failing to capture scenarios where agents must actively reroute around impassable bottlenecks. To bridge this gap, this paper introduces AgentHeal, a comprehensive benchmark