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

arXiv: https://arxiv.org/abs/2508.04575 · HTML: https://mlsanity.com/paper/2508.04575/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 26 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 5 of 5)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [LLM-based Human Simulations Have Not Yet Been Reliable](https://mlsanity.com/paper/2501.08579/) (2025)

## Built on by (most cited first, 7 of 7)

- [Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics](https://mlsanity.com/paper/2510.09901/) (2025)
- [Learning to Predict Future-Aligned Research Proposals with Language Models](https://mlsanity.com/paper/2603.27146/) (2026)
- [Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation](https://mlsanity.com/paper/2604.18005/) (2026)
- [Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey](https://mlsanity.com/paper/2511.07448/) (2025)
- [Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMs](https://mlsanity.com/paper/2604.08016/) (2026)
- [Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2509.09629/) (2025)
- [Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration](https://mlsanity.com/paper/2610.01244/) (2026)

## Abstract (arXiv)

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.