dair-ai's top AI papers of the week: s3, AutoRefine, agent scaling
dair_ai · x · 2026-11-16
dair-ai published its Top AI Papers of the Week (Nov 9–15), including s3 (arguing multi-agent systems inherit rigid designer-written orchestration that duplicates work), WikiTrace, AutoRefine, LongCapHarness, RSI for Pre-training, Self-Organized Memories, Verified Quantum Programs, and Simple Scaling of Agent Swarms.
More from AGI Musings
- AI researcher says his job is now almost fully automatable with Claude Code — jonkhler · 2026-11-16
- Bank AI ROI: 80% Say It Works, Only 1% Can Prove It, Turrin Newsletter Finds — mikeflache · 2026-11-16
- Arrow's Impossibility Theorem Invoked to Argue AI Alignment Is Mathematically Impossible — mikeflache · 2026-11-16
- AI detection reveals many contemporary fiction professionals don't read or write — Afinetheorem · 2026-11-16
- Nina Schick: keeping AI out of China is impossible — the US must just build the best AI — NinaDSchick · 2026-11-16
- Frontier lab researcher: 'We don't know how to reliably instil values into AIs' — scientific consensus — wfithian · 2026-11-16