Guardrails removed spam, off-topic, unclear, or duplicate replies.
Ask a question below.
Published answers will appear here.
was excited to cover my group's work at this workshop, focusing on failures of agents w.r.t. human-facing aspects, like social intelligence, theory of mind, user reliance, and agentic and user-facing safety! Papers in 🧵 https://twitter.com/wzenus/status/2075366037307207916
First I covered LLM failures of Theory of Mind; our recently accepted #COLM2026 paper "Social World Models" unlocks new levels of social reasoning: https://arxiv.org/abs/2509.00559 (led by @nlpxuhui )
was excited to cover my group's work at this workshop, focusing on failures of agents w.r.t. human-facing aspects, like social intelligence, theory of mind, user reliance, and agentic and user-facing safety! Papers in 🧵 https://twitter.com/wzenus/status/2075366037307207916
Guardrails removed spam, off-topic, unclear, or duplicate replies.
Ask a question below.
Published answers will appear here.