ICML Workshop Explores Agent Decision-Making and Social Intelligence
wzenus · x · 2026-07-10
At the ICML FAGEN workshop, Greg shared research on LLM agents making better decisions under uncertainty and cost, exploring when an agent should retrieve, ask, experiment, or stop. Additionally, the first speaker, Maarten Sap, discussed the social intelligence of AI agents, including structured social world models and uncertain communication, analyzing how agents understand social contexts and influence human reliance.
Related event: ICML 2026 FAGEN Workshop Spotlights AI Agent Failure Modes(11 posts)→
More from AGI Musings
- ~25% of NBER economics papers now contain AI-generated text, study finds — JeremyNguyenPhD · 2026-09-11
- Why So Many AI Researchers Think the Machines Could Kill Everyone — connoraxiotes · 2026-09-11
- jjvincent invokes Terence Tao: ceding exploration to AI means ceding human agency — jjvincent · 2026-09-11
- OpenRouter agents now out-consume humans as AI usage arrives in three waves — AccBalanced · 2026-09-11
- If AI teleports us to solutions, how do underlying fields develop? — jjvincent · 2026-09-11
- Op-ed: the ">10% extinction" narrative is liability evasion — AI is just software, and the vendor is the defendant — gerardsans · 2026-09-11