Simons Institute hosts week-long workshop on AI agent reliability at UC Berkeley, Oct 5-9
SharonYixuanLi · x · 2026-09-23
The Simons Institute is hosting a week-long workshop on the reliability of AI agents, October 5-9 at Calvin Lab Auditorium, UC Berkeley.
- Registration includes livestream access and early access to recordings for those who can't attend in person
- Speaker lineup spans academia and industry: Leman Akoglu (CMU), Anastasios Angelopoulos (Arena), Elias Bareinboim (Columbia), Moses Charikar (Stanford), Adji Bousso Dieng (Princeton), Soheil Feizi and Mohit Iyyer (UMD), Adam Kalai (RESI), and more
A noteworthy event for researchers working on agent evaluation and reliability.
More from Research
- Xiaomi's MiMo 2.6 Pro formalizes Li-Yorke chaos theorem in Lean 4 with 6,000+ verified lines — Dr_Singularity · 2026-09-23
- Open benchmarks are broken: models regex out offloaded answers, researcher argues — a1zhang · 2026-09-23
- C-HD algorithm beats Dijkstra only narrowly in an exotic regime, prompting RSI skepticism — teortaxesTex · 2026-09-23
- MLSys 2027 opens submissions with Song Han and Rashmi Vinayak as PC Co-Chairs — songhan_mit · 2026-09-23
- Tri-PvP benchmark exposes visual bias in omni-modal LLMs via evidence conflicts — Yen-Ting Piao · 2026-09-23
- 10K-run test: LLM hits 99.91% on 30-digit multiplication, 99.8% on division — srchvrs · 2026-09-23