Beyond Brainstorming: What Drives High-Quality Scientific Ideas? Lessons from Multi-Agent Collaboration

TL;DR

This paper demonstrates that structured multi-agent discussions, especially with diverse expertise and leadership, significantly enhance the quality of scientific ideas compared to solitary efforts, informing better collaborative AI design.

Contribution

It introduces a multi-agent framework for scientific ideation, systematically analyzing how team structure and diversity impact idea quality, surpassing single-agent approaches.

Findings

Multi-agent discussions outperform solitary baselines.

Leadership enhances idea integration and vision.

Diversity and expertise are key drivers of quality.

Abstract

While AI agents show potential in scientific ideation, most existing frameworks rely on single-agent refinement, limiting creativity due to bounded knowledge and perspective. Inspired by real-world research dynamics, this paper investigates whether structured multi-agent discussions can surpass solitary ideation. We propose a cooperative multi-agent framework for generating research proposals and systematically compare configurations including group size, leaderled versus leaderless structures, and team compositions varying in interdisciplinarity and seniority. To assess idea quality, we employ a comprehensive protocol with agent-based scoring and human review across dimensions such as novelty, strategic vision, and integration depth. Our results show that multi-agent discussions substantially outperform solitary baselines. A designated leader acts as a catalyst, transforming discussion into more integrated and visionary proposals. Notably, we find that cognitive diversity is a primary driver of quality, yet expertise is a non-negotiable prerequisite, as teams lacking a foundation of senior knowledge fail to surpass even a single competent agent. These findings offer actionable insights for designing collaborative AI ideation systems and shed light on how team structure influences creative outcomes.