一句话：提出记忆引导的多智能体提示协同演化框架MemCo，提升工业漏洞检测精度并大幅降低token开销。
基于LLM的多智能体漏洞检测在工业部署中存在两个问题：各智能体提示独立优化，损害全局端到端性能；演化式提示搜索缺乏迭代记忆，造成冗余计算。为此提出MemCo：采用端到端提示协同演化，以系统最终输出而非单个智能体评估提示，每轮只演化对误分类负责的智能体提示；并利用成功/失败修改记录引导搜索，减少盲目探索。在公开基准上Macro-F1提升8.4–18.0点，专有工业基准相对提升最高36.9%，单代演化token减少48.5%，推理token减少63.8%，已部署于生产安全流水线。
Large Language Model (LLM)-based multi-agent systems have shown promise for automated vulnerability detection, but our industrial deployment reveals two limitations: 1) each agent's prompt is typically optimized in isolation, degrading global end-to-end performance; and 2) evolutionary prompt search lacks memory across iterations, wasting computation costs. To address these limitations, we propose MemCo, a memory-guided prompt co-evolution framework applied to industrial vulnerability detection. First, MemCo takes an end-to-end prompt co-evolution strategy, which evaluates prompts based on the system's final output rather than assessing each agent in isolation. In each evolutionary iteration, only the prompts of agents responsible for the misclassification undergo further evolution, thereby enhancing the system's global accuracy. Second, MemCo adopts a memory-guided search mechanism, which edits prompts based on records of successful and failed modifications. This reduces redundant blind exploration and significantly lowers computation costs. Comprehensive experiments show that MemCo improves Macro-F1 by +8.4 to +18.0 points on public benchmarks and up to 36.9% relative improvement on a proprietary industrial benchmark, while reducing per-generation evolution tokens by 48.5% and inference tokens by 63.8%. MemCo is deployed as a vulnerability detection assistant in our production security pipeline.
@inproceedings{paperbot12290,
title = {No Isolated Evolution, No Blind Search: Memory-Guided Prompt Co-evolution for Industrial Multi-agent Vulnerability Detection},
author = {Jie Xu and Zihan Wu and Yun Peng and Chun Yong Chong and Linghan Meng and Kui Liu and Xiaohua Jia},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834522}
}