LATIDIA · Investigación

Orquestación consciente de la competencia para sistemas multiagente basados en LLM

arXiv: 2610.13144v1Tipo de anuncio: nuevo Resumen: Los sistemas multiagente (MAS) basados en LLM han surgido como un paradigma prometedor para mejorar el razonamiento complejo a través de la especialización y la colaboración de roles, pero un desafío clave

La noticia

arXiv:2610.13144v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have emerged as a promising paradigm for enhancing complex reasoning through role specialization and collaboration, yet a key challenge remains: how can collaboration be adapted to a backbone's competence on the current query? This problem matters because more collaboration is not always better--richer coordination may help on difficult cases, but it also incurs additional token cost and redundant interactions. We propose a two-stage competence-aware framework for automatic MAS orchestration. It first models the LLM backbone's task-conditioned competence for the current query, and then uses this signal to adapt role activation and the communication graph. Across six benchmarks, our method achieves an