Researcher calls for perturbation-based multi-agent studies over one-off swarm observations
sebkrier · x · 2026-09-11
Seb Krier critiques papers that test one specific multi-agent setup and describe the resulting swarm behavior — interesting, but hard to extrapolate: what if you change models or the environment? He argues the field should focus on perturbations and variations, narrowing down the conditions behind particular behaviors. The goal: conclusions like "under conditions X, swarms with property Y tend to do Z, but when A is present they fail to do Z regardless of Y."
More from Research
- World Model RL Debiasing Cuts Cost of Scaling Autonomous Research Agents — illinois · 2026-09-11
- RL-trained agents should carry a strong simulation prior, argues vooooogel — voooooogel · 2026-09-11
- Histed: even if the Navier-Stokes step borrowed human results, AI math progress is real — HistedLab · 2026-09-11
- Humansand launches to simulate humans for RLHF data — gharik · 2026-09-11
- Abstract CoT: latent reasoning cuts tokens up to 11.6x with CoT-level performance — evijit · 2026-09-11
- One person with an AI agent cut Google's quantum ECDSA circuit cost 52%; crowd beat it in 73 hours — anselm · 2026-09-11