Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-Solving

TL;DR

This paper introduces synthetic deliberation, a novel LLM-based method that simulates multi-perspective discourse to enhance complex problem-solving, surpassing mental simulation limitations and aiding strategic decision-making.

Contribution

It presents a new approach using large language models to simulate multi-agent deliberation, enabling parallel perspective exploration and synthesis in problem-solving.

Findings

Enables concurrent processing of multiple viewpoints.

Allows precise control over viewpoint synthesis.

Outperforms mental simulation in cognitive flexibility.

Abstract

Complex problem-solving requires cognitive flexibility--the capacity to entertain multiple perspectives while preserving their distinctiveness. This flexibility replicates the "wisdom of crowds" within a single individual, allowing them to "think with many minds." While mental simulation enables imagined deliberation, cognitive constraints limit its effectiveness. We propose synthetic deliberation, a Large Language Model (LLM)-based method that simulates discourse between agents embodying diverse perspectives, as a solution. Using a custom GPT-based model, we showcase its benefits: concurrent processing of multiple viewpoints without cognitive degradation, parallel exploration of perspectives, and precise control over viewpoint synthesis. By externalizing the deliberative process and distributing cognitive labor between parallel search and integration, synthetic deliberation transcends mental simulation's limitations. This approach shows promise for strategic planning, policymaking, and conflict resolution.