LATIDIA · Investigación

Humaniza a los agentes de las Olimpiadas: un flujo de trabajo de varias sesiones para la resolución de problemas de las Olimpiadas con Resolver, Revisar, Wiki, Verificar

arXiv: 2610.13632v1Tipo de anuncio: nuevo Resumen: Los agentes del modelo de lenguaje grande (LLM) están mejorando rápidamente en las tareas científicas y olímpicas de largo horizonte. Los sistemas recientes han producido una resolución Lean-formalizada del Navi

La noticia

arXiv:2610.13632v1 Announce Type: new Abstract: Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized resolution of the Navier--Stokes problem and autonomous solutions to four open questions in the Erd\H{o}s Conjectures database. Yet neither system releases both its underlying model and complete inference stack. More broadly, a single agent session remains brittle on difficult problems: early errors can propagate, missing domain knowledge can stall progress, and apparent success can mask a misinterpretation or weakening of the original task. We introduce HOA (Humanize Olympiads Agent), an open, flow-level framework that coordinates multiple agent sessions through three complementary feedback channels. First, an