用多智能体辩论提升分子设计的结构推理能力
Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
- 通过生成-辩论-优化循环实现多视角动态推理
- 在ChEBI-20上达到59.82%精确匹配，S²-Bench为50.52%加权成功率
- 适合需要复杂结构约束的药物分子生成任务
文本引导的分子设计是人工智能驱动药物发现的关键能力，但将自然语言指令与非线性分子结构在严格化学约束下对齐仍具挑战。现有方法如RAG、CoT提示、微调或强化学习，大多依赖少量特定推理视角，采用一次性生成流程。而真实药物研发依赖动态多视角批判与迭代优化，以协调语义意图与结构可行性。为此，我们提出Mol-Debate，一种通过迭代生成-辩论-优化循环实现动态推理的新范式。我们识别并解决该范式中的关键挑战，包括开发者-辩论者冲突、全局-局部结构推理以及静态-动态集成问题。实验表明，Mol-Debate在强基线模型上表现优异，在ChEBI-20上达到59.82%精确匹配率，在S²-Bench上取得50.52%加权成功率。代码已开源：https://github.com/wyuzh/Mol-Debate。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。