Aggression emerges in fish simulation without explicit social rules
tweetsatpreet · x · 2026-07-29
- Even without explicit social rules, the agents spontaneously exhibit competitive behavior during foraging, including chasing and biting.
- Their aggression emerges because being bitten by larger fish carries a higher penalty, not because of hand-coded social logic.
- The system reproduces a pecking order: larger fish win more often and consume more food in more unequal groups.
More from Research
- Meta Paper: Optimizing Code Execution Speed via RL Achieves Up to 200% Improvement — facebook · 2026-07-30
- OPERA: Multi-Agent Framework for Biomedical Image Analysis Without Retraining — UW · 2026-07-30
- Nature: Medical AI is heading towards a reproducibility crisis — DrDatta_AIIMS · 2026-07-30
- Anthropic Tests Claude on Robotics: Direct Control Fails, LLM Supervision Hurts Familiar Tasks — DJiafei · 2026-07-30
- Building AI Employees: Engineering Autonomous Agents to Write Linux Utilities — leebase65 · 2026-07-30
- Breaking the Correctness-Efficiency Pareto Frontier in RLVR for Code — francoisfleuret · 2026-07-30