Success bias in collective theory-building leads to systematic overestimation of theory quality, narrower search, and paradoxically lower performance when agents optimize for apparent success.
Jean-Pierre Eckmann and David Ruelle
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Derives an approximate formula for the precision of top-q selections made by a panel of n AIs with average correlation ρ.
Multi-LLM committees amplify small input perturbations into divergent deliberation trajectories and decisions under deterministic conditions.
Agent-based simulations show intrapersonal and dominant function diversity can boost or hinder performance based on context, requiring an aggregate expertise measure too.
citing papers explorer
-
Nothing Deceives Like Success: Social Learning and the Illusion of Understanding in Science
Success bias in collective theory-building leads to systematic overestimation of theory quality, narrower search, and paradoxically lower performance when agents optimize for apparent success.
-
Quantifying how AI Panels improve precision
Derives an approximate formula for the precision of top-q selections made by a panel of n AIs with average correlation ρ.
-
Collective AI can amplify tiny perturbations into divergent decisions
Multi-LLM committees amplify small input perturbations into divergent deliberation trajectories and decisions under deterministic conditions.
-
Role of diversity in team performance: the case of missing expertise, an agent based simulation
Agent-based simulations show intrapersonal and dominant function diversity can boost or hinder performance based on context, requiring an aggregate expertise measure too.