# LLM 在空间约束下的分子生成能力：3D-Fit 基准测试揭示潜力与差距

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-07-20 08:00
- AIHOT 分数：48
- AIHOT 链接：https://aihot.virxact.com/items/cmrupmrd9075jbiufe7lsmhqp
- 原文链接：https://arxiv.org/abs/2607.18144

## AI 摘要

一项新研究系统评估了通用 LLM 在结构药物设计（SBDD）中处理复杂 3D 空间约束的能力。研究者引入 3D-Fit 基准测试策略，对比 LLM 与专用扩散模型在蛋白口袋、锚定片段、药效团点及强制口袋-配体相互作用等多条件分子生成任务上的表现。结果显示，LLM 虽仍落后于 SOTA 方法，但已能同时处理多种空间约束，具备向异构场景扩展的潜力。

## 正文

Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial constraints, to generate candidate binding molecules. While diffusion models have dominated as a leading paradigm for high-quality 3D molecule generation, LLM-based methods are rapidly emerging in molecular design and have shown competitive performance in pocket-conditioned molecular generation. However, their ability to reason about physics and 3D spatial environments is largely underexplored. In this work, we systematically analyze whether current general-purpose LLMs are capable of navigating complex 3D constraints compared to established baselines such as specialized diffusion models. We consider 3D ligand generation conditioned on protein pockets together with ligand- and interaction-derived spatial constraints, including anchor fragments, pharmacophore points, and mandatory pocket-ligand interactions. To enable this evaluation, we introduce 3D-Fit - a token-efficient benchmarking strategy for assessing LLM performance on multi-conditioned spatial molecule generation. Our findings reveal a clear pattern in LLM spatial capabilities: while they still lag behind state-of-the-art approaches, they are promising and can handle multiple spatial constraints simultaneously, enabling scaling to heterogeneous setups.