LATIDIA · Investigación

LLM-IDEA: Agente experimental impulsado por la identificabilidad para el descubrimiento autónomo de modelos de mundos mecanicistas

arXiv: 2610.11253v1Tipo de anuncio: nuevo Resumen: Los agentes de modelos de lenguaje grandes se están desplegando cada vez más como científicos autónomos, diseñando experimentos e inferiendo modelos de mundo mecanicistas con una mínima sobreexigencia humana

La noticia

arXiv:2610.11253v1 Announce Type: new Abstract: Large language model agents are being increasingly deployed as autonomous scientists, designing experiments and inferring mechanistic world models with minimal human oversight. Yet identifiability is often overlooked: when a plateau is reached, the agent needs to know whether it is not yet capable enough or the model simply is not identifiable from the data, in which case no amount of further experimentation of the same kind can help. We propose the Identifiability-Driven Experimental Agent (LLM-IDEA) for closed-loop discovery with an identifiability engine that returns a three-way plateau verdict: capability limit, resolvable within the design class, or certified exhausted. On ODEBench, 60 of the 62 systems