RLCR trains LLM agents as organizations, spontaneously emerging hierarchies
rosstaylor90 · x · 2026-10-23
GenReasoning introduces RLCR (Reinforcement Learning from Collective Rewards), a recipe training LLMs as agent organizations sharing a message board and workspace, used to train Avalon-M1-Mini (120B). Findings: learned organizational hierarchies and division of labor, increased collective verification via hiring verifiers/testers, and collective thinking where agents consider helping others. Positioned as a lab for studying collective intelligence and multi-agent safety.
More from coding & agent
- Cursor agents can now drive your desktop, and one dev warns self-verifying agents just move the quality gate — petrusenko_max · 2026-10-24
- End of 'good enough software': formal verification becomes the missing AI demand curve — bookwormengr · 2026-10-24
- Dev says agents now run everything in his workflow except scrolling Shorts — tokenbender · 2026-10-24
- DAB, a cross-database agent benchmark, hits EMNLP Oral; best model only 38% pass@1 — adityagp · 2026-10-24
- Firecrawl Alexandria launches sports data APIs across 14 providers after $75M Series B — devdigest · 2026-10-24
- 27B open-source model beats GPT-5.5 and Opus 4.8 on desktop tasks at 1.5% of the cost — alex_verem · 2026-10-23