AI & ML Breaks Assumption

Groups with bounded rationality and stochasticity can outperform perfectly rational agents because randomness encodes signals lost in deterministic behavior.

arXiv · March 17, 2026 · 2603.13807

Zhihuan Huang, Yichong Xia, Yuqing Kong

The Takeaway

Challenges the assumption that agent rationality should be maximized for collective intelligence. It demonstrates that LLM ensembles benefit from specific temperature settings (quantal response) to improve reasoning accuracy on complex tasks.

From the abstract

The effectiveness of collective decision-making is often challenged by the bounded rationality and inherent stochasticity of individual agents. We investigate this by analyzing how to aggregate decisions from n experts, each receiving a private signal about an unknown state. Assuming signals are conditionally independent and identically distributed, we depart from the fully rational paradigm and model expert behavior using quantal response, a stochastic choice model capturing bounded rationality