DARC-Sched: A Data-Aware Multi-Agent Large Language Model Framework for Scalable Software Vulnerability Detection and Repair with Optimized Code Data Scheduling
DOI:
https://doi.org/10.66238/fsrma113Keywords:
Software Vulnerability Detection, Large Language Models (LLMs), Multi-Agent Systems, Data Scheduling, Retrieval-Augmented Generation, Software Security, Code IntelligenceAbstract
Software vulnerability detection and automated repair have become critical for ensuring the security and reliability of large-scale software systems, particularly in modern development environments where massive code repositories and continuous integration pipelines significantly increase the complexity of vulnerability management. However, existing approaches based on Large Language Models (LLMs) often suffer from limited scalability and inefficient code retrieval when operating on large-scale code corpora, leading to degraded detection accuracy and high inference latency. To address these challenges, this paper proposes DARC-Sched (Data-Aware Reasoning and Collaborative Scheduling framework), a Data-Aware Multi-Agent Large Language Model framework that integrates multi-agent collaborative reasoning with optimized code data scheduling mechanisms for scalable vulnerability detection and repair. Specifically, DARC-Sched employs multiple specialized agents to perform vulnerability localization, evidence retrieval, verification, patch generation, and security validation, while a hierarchical data scheduling module dynamically prioritizes and caches vulnerability-relevant code segments based on learned risk-aware access patterns. Experimental results on benchmark datasets demonstrate that DARC-Sched achieves a 2.9% improvement in F1-score over strong retrieval-augmented baselines, reaching 91.9% F1-score, while reducing average retrieval latency by approximately 33% (from 295 ms to 198 ms). These results validate that integrating data-aware scheduling with multi-agent reasoning significantly improves both detection accuracy and system efficiency in large-scale software vulnerability analysis
References
[1] Zhou, Yaqin, et al. "Devign: Effective vulnerability identification by learning comprehensive program semantics via graph neural networks." Advances in neural information processing systems 32 (2019).
[2] Li, Zhen, et al. "Vuldeepecker: A deep learning-based system for vulnerability detection." arXiv preprint arXiv:1801.01681 (2018).
[3] Feng, Zhangyin, et al. "Codebert: A pre-trained model for programming and natural languages." Findings of the association for computational linguistics: EMNLP 2020. 2020.
[4] Guo, Daya, et al. "Graphcodebert: Pre-training code representations with data flow." arXiv preprint arXiv:2009.08366 (2020).
[5] Chen, Mark, et al. "Evaluating large language models trained on code." arXiv preprint arXiv:2107.03374 (2021).
[6] Roziere, Baptiste, et al. "Code llama: Open foundation models for code." arXiv preprint arXiv:2308.12950 (2023).
[7] Tian, Runchu, et al. "Debugbench: Evaluating debugging capability of large language models." Findings of the Association for Computational Linguistics: ACL 2024. 2024.
[8] Fu, Michael, et al. "Vulrepair: a t5-based automated software vulnerability repair." Proceedings of the 30th ACM joint european software engineering conference and symposium on the foundations of software engineering. 2022.
[9] Yao, Shunyu, et al. "React: Synergizing reasoning and acting in language models." arXiv preprint arXiv:2210.03629 (2022).
[10] Shinn, Noah, et al. "Reflexion: Language agents with verbal reinforcement learning." Advances in neural information processing systems 36 (2023): 8634-8652.
[11] Yang, John, et al. "Swe-agent: Agent-computer interfaces enable automated software engineering." Advances in Neural Information Processing Systems 37 (2024): 50528-50652.
[12] Qian, Chen, et al. "Chatdev: Communicative agents for software development." Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers). 2024.
[13] Guu, Kelvin, et al. "Retrieval augmented language model pre-training." International conference on machine learning. PMLR, 2020.
[14] Lewis, Patrick, et al. "Retrieval-augmented generation for knowledge-intensive nlp tasks." Advances in neural information processing systems 33 (2020): 9459-9474.
[15] Guo, Daya, et al. "Unixcoder: Unified cross-modal pre-training for code representation." Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.
[16] Ma, Xinyin, Gongfan Fang, and Xinchao Wang. "Deepcache: Accelerating diffusion models for free." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024.
[17] Wang, Ao, et al. "{InfiniCache}: exploiting ephemeral serverless functions to build a {cost-effective} memory cache." 18th USENIX conference on file and storage technologies (FAST 20). 2020.
[18] Lin, Yuzhen, et al. "CEMG: Collaborative-Enhanced Multimodal Generative Recommendation." International Conference on Multimedia Modeling. Singapore: Springer Nature Singapore, 2026.
[19] Liang, Zucheng, et al. "Research on multi-hop inference optimization of llm based on mquake framework." arXiv preprint arXiv:2509.04770 (2025).
[20] Yao, Yilin, et al. "MSA-TransUNet: A Multi-Scale Attention Enhanced Transformer-UNet Architecture for Accurate Vessel Segmentation and Visualization in Medical Imaging." Journal of Medicine and Life Sciences 1.4 (2025): 48-57.
[21] Yao, Yilin, et al. "Deep Learning Models for Multi-class Pneumonia Detection in Chest X-rays: A Comparative Study of VGG16, MobileNet, and ResNet152." Journal of Technology Innovation and Engineering 1.4 (2025).
[22] Huang, Yanxiang, et al. "Enhancing Open-Vocabulary Panoptic Segmentation with Semantic-Guided Q-Tuning." 2025 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2025.
[23] Li, Zheyu, Yue Hao, and Peifan Zeng. "CLASNet: A Cognitive Load–Aware CNN-LSTM-Attention Framework for Supply Chain Demand Forecasting and Adaptive Human–Computer Interaction." Journal of Computer Science and Frontier Technologies 3.2 (2026): 44-57.
[24] Xu, Zitong, Yuqing Wu, and Yue Zhao. "TRIZ-RAGNER: A Retrieval-Augmented Large Language Model for TRIZ-Aware Named Entity Recognition in Patent-Based Contradiction Mining." Journal of Computer, Signal, and System Research 3.2 (2026): 56-65.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yanjing Xu, Min Qiu Trine, Huanyu Wu
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Terms (Recommended – CC BY 4.0)
All articles published in Fundamental Scientific Reports in Multidisciplinary Areas are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are properly cited. Users are allowed to copy, redistribute, remix, transform, and build upon the material for any purpose, including commercial use, as long as appropriate credit is given.
Authors retain copyright of their work while granting the journal the right of first publication. The journal provides immediate open access to its content on the principle that making research freely available supports a greater global exchange of knowledge.
For more information about this license, visit:
https://creativecommons.org/licenses/by/4.0/
