Search papers, labs, and topics across Lattice.
Mol-Debate introduces an iterative generate-debate-refine loop for text-guided molecular design, mimicking real-world drug discovery's dynamic, multi-perspective critique. It addresses challenges like developer-debater conflict and global-local structural reasoning through perspective-oriented orchestration. Experiments show Mol-Debate achieves state-of-the-art performance, reaching 59.82% exact match on ChEBI-20 and 50.52% weighted success rate on S$^2$-Bench, significantly outperforming existing RAG, CoT prompting, and fine-tuning approaches.
Forget one-shot generation: Mol-Debate's iterative debate loop unlocks state-of-the-art molecular design by dynamically reconciling semantic intent with structural feasibility.
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.
