[2601.03604] Interleaved Tool-Call Reasoning for Protein Function Understanding

Computer Science > Artificial Intelligence arXiv:2601.03604 (cs) [Submitted on 7 Jan 2026 (v1), last revised 5 Mar 2026 (this version, v2)] Title:Interleaved Tool-Call Reasoning for Protein Function Understanding Authors:Chuanliu Fan, Zicheng Ma, Huanran Meng, Aijia Zhang, Wenjie Du, Jun Zhang, Yi Qin Gao, Ziqiang Cao, Guohong Fu View a PDF of the paper titled Interleaved Tool-Call Reasoning for Protein Function Understanding, by Chuanliu Fan and 8 other authors View PDF HTML (experimental) Abstract:Recent advances in large language models (LLMs) have highlighted the effectiveness of chain-of-thought reasoning in symbolic domains such as mathematics and programming. However, our study shows that directly transferring such text-based reasoning paradigms to protein function understanding is ineffective: reinforcement learning mainly amplifies superficial keyword patterns while failing to introduce new biological knowledge, resulting in limited generalization. We argue that protein function prediction is a knowledge-intensive scientific task that fundamentally relies on external biological priors and computational tools rather than purely internal reasoning. To address this gap, we propose PFUA, a tool-augmented protein reasoning agent that unifies problem decomposition, tool invocation, and grounded answer generation. Instead of relying on long unconstrained reasoning traces, PFUA integrates domain-specific tools to produce verifiable intermediate evidence. Experiments on fo...