多智能体协作比单个智能体更易产生高质量科研创意。
Beyond Brainstorming: What Drives High-Quality Scientific Ideas? Lessons from Multi-Agent Collaboration
- 设计多智能体协作框架，模拟真实科研讨论过程。
- 有领导的多智能体团队提案新颖性与整合度显著更高。
- 认知多样性促进创新，但需基础专业能力支撑。
尽管人工智能在科学创意生成方面展现潜力，但现有框架多依赖单智能体优化，受限于知识和视角边界。受真实科研协作启发，本文研究结构化多智能体讨论是否优于独立构思。提出一种合作式多智能体框架生成研究提案，并系统比较团队规模、有无领导者、跨学科性与资历构成等配置。通过智能体评分与人工评审相结合的综合评估协议，从新颖性、战略视野、融合深度等维度衡量创意质量。结果表明，多智能体讨论显著优于单智能体基线；指定领导者能推动讨论向更整合、更具远见的方向发展。值得注意的是，认知多样性是质量提升的关键驱动力，但专业知识是不可替代的前提，缺乏资深成员的团队无法超越单一熟练智能体的表现。研究为设计协同型AI创意系统提供可操作洞见，并揭示团队结构对创造性成果的影响机制。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。