LATIDIA · Investigación

JevAgentHarness: Evaluación comparativa, implementación y capacitación de modelos de decisión que comparten el control con los LLM

arXiv: 2610.21412v1Tipo de anuncio: nuevo Resumen: los agentes del modelo de lenguaje grande (LLM) ahora arreglan el software, operan los ordenadores y sirven a los clientes, pero sus arneses, los programas que los ejecutan, llaman a un LLM grande en cada paso,

La noticia

arXiv:2610.21412v1 Announce Type: new Abstract: Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large LLM at every step, which makes long tasks slow and costly. Most of these calls end in a multiple-choice decision, such as which tool to call next. Decision models such as Jev answer these questions directly, at a fraction of an LLM call's time and price. We ask how a harness can delegate these decisions to a decision model with little loss of success. To evaluate decision models in agentic tasks, we build AgentDecisionBench, which tests them from isolated questions up