Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design

TL;DR

Mol-Debate introduces an iterative multi-agent debate framework to enhance structural reasoning in text-guided molecular design, significantly improving accuracy over existing methods.

Contribution

It presents a novel debate-based generation paradigm that facilitates dynamic, multi-perspective critique and refinement in molecular design tasks.

Findings

Achieves 59.82% exact match on ChEBI-20

Attains 50.52% weighted success rate on S$^2$-Bench

Outperforms strong baselines in chemical structure generation

Abstract

Text-guided molecular design is a key capability for AI-driven drug discovery, yet it remains challenging to map sequential natural-language instructions with non-linear molecular structures under strict chemical constraints. Most existing approaches, including RAG, CoT prompting, and fine-tuning or RL, emphasize a small set of ad-hoc reasoning perspectives implemented in a largely one-shot generation pipeline. In contrast, real-world drug discovery relies on dynamic, multi-perspective critique and iterative refinement to reconcile semantic intent with structural feasibility. Motivated by this, we propose Mol-Debate, a generation paradigm that enables such dynamic reasoning through an iterative generate-debate-refine loop. We further characterize key challenges in this paradigm and address them through perspective-oriented orchestration, including developer-debater conflict, global-local structural reasoning, and static-dynamic integration. Experiments demonstrate that Mol-Debate achieves state-of-the-art performance against strong general and chemical baselines, reaching 59.82% exact match on ChEBI-20 and 50.52% weighted success rate on S$^2$-Bench. Our code is available at https://github.com/wyuzh/Mol-Debate.