Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning

• URL: http://arxiv.org/abs/2511.08024v1
• Date: Wed, 12 Nov 2025 01:34:45 GMT
• Title: Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
• Authors: Tianwen Lyu, Xiang Zhuang, Keyan Ding, Xinzhe Cao, Lei Liang, Wei Zhao, Qiang Zhang, Huajun Chen,
• Abstract summary: Biomolecular mechanisms require multi-step reasoning across molecular interactions, signaling cascades, and metabolic pathways.<n>Existing approaches often exacerbate these issues: reasoning steps may deviate from biological facts or fail to capture long mechanistic dependencies.<n>We propose a Knowledge-Augmented Long-CoT Reasoning framework that integrates LLMs with knowledge graph-based multi-hop reasoning chains.
• Score: 51.673503054645415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design [0.9332987715848714]
  Large Language Models (LLMs) promise to accelerate discovery by reasoning across the expanding scientific landscape.<n>In materials science, where innovation demands integrating concepts from molecular chemistry to mechanical performance, this is especially acute.<n>We introduce a multi-agent framework guided by large-scale knowledge graphs to find sustainable substitutes for per- and polyfluoroalkyl substances (PFAS)-chemicals.
  arXiv  Detail & Related papers  (2026-02-07T10:50:34Z)
• Progressive Multi-Agent Reasoning for Biological Perturbation Prediction [32.71169480836875]
  We present LINCSQA, a novel benchmark for predicting target gene regulation under complex chemical perturbations.<n>We also propose PBio-Agent, a multi-agent framework that integrates difficulty-aware task sequencing with iterative knowledge refinement.<n>Our key insight is that genes affected by the same perturbation share causal structure, allowing confidently predicted genes to contextualize more challenging cases.
  arXiv  Detail & Related papers  (2026-02-07T06:59:44Z)
• How well can off-the-shelf LLMs elucidate molecular structures from mass spectra using chain-of-thought reasoning? [51.286853421822705]
  Large language models (LLMs) have shown promise for reasoning-intensive scientific tasks, but their capability for chemical interpretation is still unclear.<n>We introduce a Chain-of-Thought (CoT) prompting framework and benchmark that evaluate how LLMs reason about mass spectral data to predict molecular structures.<n>Our evaluation across metrics of SMILES validity, formula consistency, and structural similarity reveals that while LLMs can produce syntactically valid and partially plausible structures, they fail to achieve chemical accuracy or link reasoning to correct molecular predictions.
  arXiv  Detail & Related papers  (2026-01-09T20:08:42Z)
• BIOME-Bench: A Benchmark for Biomolecular Interaction Inference and Multi-Omics Pathway Mechanism Elucidation from Scientific Literature [12.185152549393152]
  BIOME-Bench is constructed via a rigorous four-stage workflow to evaluate two core capabilities of large language models (LLMs) in multi-omics analysis.<n>We develop evaluation protocols for both tasks and conduct comprehensive experiments across multiple strong contemporary models.
  arXiv  Detail & Related papers  (2025-12-31T09:01:27Z)
• Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning [75.79451512757844]
  Foundation models exhibit broad knowledge but limited task-specific reasoning.<n> RLVR and inference scaling motivate post-training strategies such as RLVR and inference scaling.<n>We show that RLVR induces a squeezing effect, reducing reasoning entropy and forgetting some correct paths.
  arXiv  Detail & Related papers  (2025-11-10T18:25:26Z)
• Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs [78.18336140706471]
  Sci-LLMs have emerged as a promising frontier for accelerating biological discovery.<n>Current strategies limit Sci-LLMs' reasoning capacity when processing raw biomolecular sequences.<n>We show that a more effective strategy is to provide Sci-LLMs with high-level structured context.
  arXiv  Detail & Related papers  (2025-10-27T09:03:21Z)
• $\ ext{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models [59.125833618091846]
  We propose a multi-view framework that integrates three perspectives: the molecular structure view, the molecular task view, and the molecular rules view.<n>Experiments demonstrate that $textM2$LLM achieves state-of-the-art performance on multiple benchmarks across classification and regression tasks.
  arXiv  Detail & Related papers  (2025-08-12T05:46:47Z)
• Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery [21.895481477176475]
  Mol-R1 is a novel framework designed to improve explainability and reasoning performance of R1-like Explicit Long-CoT reasoning models in text-based molecule generation.<n>MoIA, Molecular Iterative Adaptation, is a training strategy that iteratively combinesSupervised Fine-tuning (SFT) with Reinforced Policy Optimization (RPO) to boost the reasoning performance of R1-like reasoning models for molecule discovery.
  arXiv  Detail & Related papers  (2025-08-11T18:50:05Z)
• BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model [12.528834366422466]
  BioReason learns to produce logical, biologically coherent deductions.<n>It boosts KEGG-based disease pathway prediction accuracy from 86% to 98%.<n>It also improves variant effect prediction by an average of 15% over strong baselines.
  arXiv  Detail & Related papers  (2025-05-29T15:49:27Z)
• BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning [49.487327661584686]
  We introduce BioMaze, a dataset with 5.1K complex pathway problems from real research.<n>Our evaluation of methods such as CoT and graph-augmented reasoning, shows that LLMs struggle with pathway reasoning.<n>To address this, we propose PathSeeker, an LLM agent that enhances reasoning through interactive subgraph-based navigation.
  arXiv  Detail & Related papers  (2025-02-23T17:38:10Z)
• Molecular Odor Prediction Based on Multi-Feature Graph Attention Networks [11.912107063761939]
  Quantitative Structure-Odor Relationship task involves predicting associations between molecular structures and their corresponding odors.<n>We propose a method for QSOR, utilizing Graph Attention Networks to model molecular structures and capture both local and global features.<n>Our approach demonstrates clear advantages in QSOR prediction tasks, offering valuable insights into the application of deep learning in cheminformatics.
  arXiv  Detail & Related papers  (2025-02-03T15:11:24Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph [29.447300472617826]
  Think-on-Graph (ToG) is a new approach for external knowledge graphs (KG) in large language models (LLMs) ToG iteratively executes beam search on KG, discovers the most promising reasoning paths, and returns the most likely reasoning results. ToG achieves overall SOTA in 6 out of 9 datasets where most previous SOTAs rely on additional training.
  arXiv  Detail & Related papers  (2023-07-15T03:31:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.