用智能体探索修复无效分子结构，保留原始设计意图。
Agentic Molecular Recovery via Molecule-Aware Exploration
- 通过分子感知的不匹配追踪与多候选路径探索，实现精准修复。
- 在三个基线模型生成的20个无效分子上，恢复效果最优。
- 适合需要高保真分子生成的药物研发人员使用。
基于大语言模型的文本引导分子生成常产生无效SMILES。我们提出，应从关注有效性的修复转向保持分子身份的恢复：不仅要恢复化学有效性，还需保留目标相关的结构特征，还原描述所暗示的分子身份。这一视角揭示了现有修正策略的局限性：事后修复会扭曲关键结构，纯大模型修正引入全局漂移，通用智能体修正受限于贪婪的单候选轨迹，即使使用可执行的RDKit编辑工具也难以突破。为此，我们提出AMREC，结合分子感知的不匹配追踪、扩展候选探索与轨迹级选择。在三个主干模型生成的20个无效ChEBI分子上，AMREC在结构、精确匹配和字符串级指标上均表现最佳。
原文摘要 · Abstract (English)
Text-guided molecular generation with LLMs often yields invalid SMILES. We argue that invalid drafts should be addressed through a shift from validity-oriented repair to identity-preserving molecular recovery: the objective is not only to restore chemical validity, but also to preserve target-relevant structural cues and recover the molecular identity implied by the description. This perspective reveals the limitations of existing correction strategies. Post-hoc repair can recover validity while distorting key structures, LLM-only correction can introduce unintended global drift, and generic agentic correction remains constrained by greedy single-candidate trajectories even when equipped with executable RDKit edit tools. To address these limitations, we propose AMREC, which couples molecule-aware mismatch tracking with expanded candidate exploration and trajectory-level selection. On invalid ChEBI-20 drafts from three backbone models, AMREC achieves the strongest overall recovery profile across structural, exact-match, and string-level metrics.
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。