LATIDIA · Investigación

Cuando los agentes de LLM no leen la sala: readaptarse para el razonamiento social relacional

arXiv:2609.25284v1 Anuncio Tipo: nuevo Resumen: Las decisiones más básicas de un agente social (¿debo reaccionar a esta publicación? ¿a quién debo contactar?) no son problemas puramente de contenido. La acción correcta a menudo depende de la latente

La noticia

arXiv:2609.25284v1 Announce Type: new Abstract: A social agent's most basic decisions (should I react to this post? who should I reach out to?) are not purely content problems. The right action often hinges on the latent relationship between people -- tie strength, reciprocity, mutual connections -- rather than on which content is most salient. Standard LLM agent loops do not explicitly represent how new relational evidence should revise the agent's current social hypothesis, leaving them prone to surface-obvious choices when relational and content cues diverge. We formalize this failure mode with a relationship-reasoning benchmark: 500 synthetic social worlds with friendships, follows, reaction histories, and feeds, yielding 1,000 queries over two