Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
This addresses a key problem in AI-driven drug discovery by enabling dynamic, multi-perspective reasoning to reconcile semantic intent with structural feasibility, representing a novel approach rather than an incremental improvement.
The paper tackles the challenge of text-guided molecular design by proposing Mol-Debate, a multi-agent debate paradigm that improves structural reasoning, achieving state-of-the-art results with 59.82% exact match on ChEBI-20 and 50.52% weighted success rate on S^2-Bench.
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.