UrbanLLMind: 10k memory-equipped LLM agents simulate a week of real San Francisco movement
anas_ant · x · 2026-09-09
UrbanLLMind, accepted at COLM 2026, simulates a real city (San Francisco) with 10,000 persistent LLM agents featuring memory, social networks, and family dynamics, validated against real travel data.
The study builds on the authors' previous award-winning urban simulation work and tests whether thousands of LLM agents can move through a city like real people over a full week.
More from Research
- Prompt optimizer GEPA lifts Meta Muse Spark 1.1 success from 22.2% to 100% while cutting queries to 0.3% — iamrobotbear · 2026-09-09
- Terence Tao weighs the tradeoff: 100 solutions, 90 publication-quality writeups, 10 left behind — tak3sh8 · 2026-09-09
- Terence Tao on how new tools flatten math's difficulty landscape while expanding its frontiers — burny_tech · 2026-09-09
- UCLA professor challenges Anandkumar's Euler singularity paper: stability proof still unfinished — lpachter · 2026-09-09
- Jim Fan declares VLA dead: multimodal coding is the right action space for robotics' System 2 — DrJimFan · 2026-09-09
- Team takes 1st on public leaderboard of PhysAI Dynamic 4D Reconstruction Challenge with Flow4R+ — elliottszwu · 2026-09-09