When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning

arXiv cs.AISeptember 23, 2026en

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, reac

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Agenter