Interleaved Tool-Call Reasoning for Protein Function Understanding

2026-01-07

arXiv.org

AI Summary

Traditional large language models are limited in protein function understanding tasks due to fixed knowledge and insufficient generalization capabilities. This work proposes PFUA, a tool-augmented reasoning agent that, for the first time, integrates problem decomposition, tool invocation, and evidence generation into protein function prediction. PFUA leverages domain-specific bioinformatics tools to produce verifiable intermediate evidence, effectively combining external biological priors with interleaved reasoning to overcome the constraints of purely text-based inference. Evaluated across four benchmark datasets, PFUA achieves an average performance improvement of 103% over existing language model–only approaches, demonstrating significant superiority in predictive accuracy and biological interpretability.

Technology Category

• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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 four benchmarks demonstrate that PFUA consistently outperforms text-only reasoning models with an average performance improvement of 103%.

Problem

• protein function understanding
• chain-of-thought reasoning
• knowledge-intensive task
• biological priors
• generalization

Innovation

• tool-augmented reasoning
• protein function prediction
• knowledge-intensive reasoning
• interleaved tool-call
• biological priors