用动态组合工具提升化学AI性能，小样本下效果更优
ChemAmp: Amplified Chemistry Tools via Composable Agents
- 将化学工具拆解为可组合的智能体，动态构建任务专用超智能体
- 仅需10个样本即超越专业模型，在4项化学任务中表现领先
- 推理成本降低94%，适合资源有限但追求高效的研究场景
尽管基于大模型的智能体在科学领域（尤其是化学）已证明具备工具编排能力，但其单任务表现仍受限于底层工具的约束。为此，我们提出工具放大（tool amplification）新范式，通过在单个任务内优化、动态协调专精工具，增强整体能力。在此框架下，我们推出ChemAmp——一个计算轻量的系统，将化学工具（如UniMol2、Chemformer）作为可组合的构建块智能体，动态构建任务专用的超智能体，可在极少数据（≤10样本）条件下突破单一工具限制。在分子设计、分子描述生成、反应预测和性质预测四项核心化学任务上的评估表明，ChemAmp优于化学专用模型、通用大模型及具备工具编排能力的智能体系统。关键在于，该自底向上的构建策略使推理令牌成本相较传统多智能体系统降低94%。
原文摘要 · Abstract (English)
Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance remains limited by underlying tool constraints. To this end, we propose tool amplification, a novel paradigm that enhances the collective capabilities of specialized tools through optimized, dynamic coordination within individual tasks. Instantiating this paradigm, we introduce ChemAmp, a computationally lightweight framework that dynamically treats chemistry tools (e.g., UniMol2, Chemformer) as composable building-block agents. It constructs task-specialized super-agents that transcend atomic tool constraints with limited data ($\leq$10 samples). Our evaluations across four core chemistry tasks molecular design, molecule captioning, reaction prediction, and property prediction demonstrate that ChemAmp outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration. Critically, this bottom-up construction strategy enables 94\% inference token cost reductions versus vanilla multi-agent systems.
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。