arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01815cs.AI
收藏

INDIBATOR: 多样且基于事实的个体性用于分子发现中的多智能体辩论

INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院);Yonsei university(延世大学)

Yunhui Jang, Seonghyun Park, Jaehyung Kim, Sungsoo Ahn

AI总结:

INDIBATOR 通过基于个性化科学家资料的多智能体辩论框架,在分子发现中实现了更高质量的科学发现。

摘要:

多智能体系统已经 emerged 作为自动化科学发现的强大范式。为了在多智能体系统中区分智能体行为,当前框架通常分配通用的角色基于人设,如“评审员”或“撰写者”,或依赖于粗粒度的关键词基于人设。虽然有效,但这种方法过于简化了人类科学家的操作方式,其贡献受其独特研究轨迹的影响。为此,我们提出 INDIBATOR,一个用于分子发现的框架,该框架使智能体基于从两种模态中构建的个性化科学家资料而扎根:出版历史用于文献衍生的知识和分子历史用于结构先验。这些智能体通过提案、批评和投票阶段进行多轮辩论。我们的评估显示,这些基于细粒度个体性的智能体在依赖于粗粒度人设的系统上始终表现更优,实现了竞争性或最先进水平的表现。这些结果验证了捕捉“科学DNA”对于个体智能体至关重要,以实现高质量的发现。

英文摘要:

Multi-agent systems have emerged as a powerful paradigm for automating scientific discovery. To differentiate agent behavior in the multi-agent system, current frameworks typically assign generic role-based personas such as ''reviewer'' or ''writer'' or rely on coarse grained keyword-based personas. While functional, this approach oversimplifies how human scientists operate, whose contributions are shaped by their unique research trajectories. In response, we propose INDIBATOR, a framework for molecular discovery that grounds agents in individualized scientist profiles constructed from two modalities: publication history for literature-derived knowledge and molecular history for structural priors. These agents engage in multi-turn debate through proposal, critique, and voting phases. Our evaluation demonstrates that these fine-grained individuality-grounded agents consistently outperform systems relying on coarse-grained personas, achieving competitive or state-of-the-art performance. These results validate that capturing the ``scientific DNA'' of individual agents is essential for high-quality discovery.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑