Decision Aggregation under Quantal Response
This work addresses collective decision-making challenges for AI and social systems by revealing how bounded rationality can enhance group performance, though it is incremental in applying existing models to new contexts.
The paper tackled the problem of aggregating decisions from bounded rational experts by modeling them with quantal response, showing that majority voting is optimal under certain rationality thresholds and can outperform fully rational agents. Validation using large language models demonstrated that aggregating stochastic outputs improves accuracy on complex reasoning tasks.
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. Within a minimax regret framework, we show that majority voting is the optimal robust aggregator when individual rationality falls below a certain threshold. Interestingly, such groups can outperform perfectly rational agents, as their decision randomness encodes weak but informative signals lost in deterministic behavior. We validate these findings using large language models (LLMs), which naturally exhibit quantal response via their temperature parameter. Aggregating moderately stochastic LLM outputs significantly improves accuracy on complex reasoning tasks, highlighting bounded rationality not as a limitation, but as a potential strength in collective intelligence.