Interleaved Tool-Call Reasoning for Protein Function Understanding
This addresses the challenge of knowledge-intensive protein function prediction for biologists and computational researchers, offering a novel approach that is not purely incremental but builds on tool-augmented reasoning.
The paper tackles the problem of protein function understanding by showing that direct transfer of text-based reasoning paradigms is ineffective, and proposes PFUA, a tool-augmented agent that integrates domain-specific tools, achieving an average performance improvement of 103% over text-only models on four benchmarks.
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 four benchmarks demonstrate that PFUA consistently outperforms text-only reasoning models with an average performance improvement of 103%.