@inproceedings{li-etal-2026-chemamp,
    title = "{C}hem{A}mp: Amplified Chemistry Tools via Composable Agents",
    author = "Li, Zhucong  and
      Chang, Powei  and
      Xiao, Jin  and
      Zhou, Zhijian  and
      He, Qianyu  and
      Liang, Jiaqing  and
      Cao, Fenglei  and
      Yinghui, Xu  and
      Qi, Yuan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.52/",
    pages = "1038--1053",
    ISBN = "979-8-89176-395-1",
    abstract = "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 ({\ensuremath{\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."
}