Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning

TL;DR

This paper introduces a knowledge-augmented reasoning framework that enhances large language models' ability to perform complex, multi-step biomolecular reasoning by integrating knowledge graphs and a new comprehensive benchmark.

Contribution

It proposes a novel framework combining LLMs with knowledge graph-based multi-hop reasoning and introduces PrimeKGQA, a new benchmark for biomolecular question answering.

Findings

Outperforms existing methods on multi-hop biomolecular reasoning tasks.

Demonstrates improved factual grounding and reasoning consistency.

Achieves state-of-the-art results on PrimeKGQA and related datasets.

Abstract

Understanding complex biomolecular mechanisms requires multi-step reasoning across molecular interactions, signaling cascades, and metabolic pathways. While large language models(LLMs) show promise in such tasks, their application to biomolecular problems is hindered by logical inconsistencies and the lack of grounding in domain knowledge. Existing approaches often exacerbate these issues: reasoning steps may deviate from biological facts or fail to capture long mechanistic dependencies. To address these challenges, we propose a Knowledge-Augmented Long-CoT Reasoning framework that integrates LLMs with knowledge graph-based multi-hop reasoning chains. The framework constructs mechanistic chains via guided multi-hop traversal and pruning on the knowledge graph; these chains are then incorporated into supervised fine-tuning to improve factual grounding and further refined with reinforcement learning to enhance reasoning reliability and consistency. Furthermore, to overcome the shortcomings of existing benchmarks, which are often restricted in scale and scope and lack annotations for deep reasoning chains, we introduce PrimeKGQA, a comprehensive benchmark for biomolecular question answering. Experimental results on both PrimeKGQA and existing datasets demonstrate that although larger closed-source models still perform well on relatively simple tasks, our method demonstrates clear advantages as reasoning depth increases, achieving state-of-the-art performance on multi-hop tasks that demand traversal of structured biological knowledge. These findings highlight the effectiveness of combining structured knowledge with advanced reasoning strategies for reliable and interpretable biomolecular reasoning.