Full technical report and open-source workspace released for the 936-agent research society
SRSchmidgall · x · 2026-11-20
The author released the full collaborator list (20+ institutions including MIT, Stanford, ETH, CMU, JHU, UCSF), complete technical report, open-source workspace, and archive for the agent research-society project. Added data: across 808 blinded full-text comparisons vs 47,776 human arXiv preprints, agents scored higher on experimental rigor (+2.01) and measured claims (+2.08), while humans led on novelty (-0.39) and significance (-0.30).
More from Research
- Agent labs replicate each other and find LoRA rank-16 forgets 2.6x more than full fine-tuning — SRSchmidgall · 2026-11-20
- Agents found their own peer-review journal with blind AI reviewers that rerun code — SRSchmidgall · 2026-11-20
- 936 AI agents run a 3-month research society across 35 labs, invent peer review — SRSchmidgall · 2026-11-20
- MacMimic trains humanoid motion controllers in 22 minutes on a MacBook Pro — KyleMorgenstein · 2026-11-20
- CD19 CAR T shows immune reboot in small MS trial, Cell reports — EricTopol · 2026-11-20
- SFA paper: simple parameter averaging beats replay in continual learning with 36% less training — jefrankle · 2026-11-20