LATIDIA · Investigación

CLASIFICACIÓN: Recuperación de la herramienta del agente de IA consciente de la fiabilidad a través de la dinámica de ejecución

arXiv: 2610.13889v1Tipo de anuncio: nuevo Resumen: A medida que los agentes de IA dependen cada vez más de herramientas externas, la recuperación precisa es esencial para un comportamiento confiable. Los métodos existentes optimizan la relevancia semántica, pero también ignoran en gran medida

La noticia

arXiv:2610.13889v1 Announce Type: new Abstract: As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RATED (Reliability-Aware Tool Retrieval via Execution Dynamics), a retrieval framework that combines robust semantic matching with dynamic reliability adaptation. RATED employs a frozen dual-encoder with contrastive fine-tuning for semantic matching, and a lightweight contextual bandit module that re-ranks candidates based on real-time execution feedback. This design enables rapid adaptation to runtime tool failures without expensive model retraining. We introduce EcoAgent, a benchmark of 5,172 real-world tools and over 210,000 query-tool pairs for