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

TL;DR

INDIBATOR introduces individualized scientist profiles for multi-agent molecular discovery, leveraging publication and molecular histories to enhance debate and decision-making, leading to improved discovery outcomes.

Contribution

The paper presents a novel framework that grounds multi-agent systems in detailed scientist profiles, surpassing traditional role-based personas in molecular discovery tasks.

Findings

Agents outperform coarse-grained systems in discovery tasks

Individualized profiles improve debate quality and decision accuracy

Achieves state-of-the-art performance in molecular discovery

Abstract

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.