跳到正文
arXiv cs.AI· Xiaoyang Xing, Wenyu Dai, Xiaoliang Gong, Asoke K Nandi, Anthony Cohn·· 1 小时前AI 评分36

L2C:LLM 引导的多智能体工作流进化实现高效自动化红队测试

Learning to Coordinate: LLM-Guided Workflow Evolution for Token-Efficient Red Teaming

AI 导读

L2C(Learning to Coordinate)是一个 LLM 引导的框架,通过版本化图谱为每个红队测试案例进化可执行的多智能体工作流,由监督微调训练的控制器决定保留、细化或重构协作。在 HarmBench 的六种执行器-目标模型配置下,L2C 的 ASR 比 EvoSynth 提升 1.4 至 4.5 个百分点,同时将平均在线 token 减少 35.6% 至 37.3%。

正文 · 原文

View PDF HTML (experimental)

Abstract:Automated red teaming is essential for identifying safety failures in large language models (LLMs), but its practical scalability depends on the resources required to discover those failures. Multi-agent systems can combine complementary capabilities, yet repeated planning, redundant exchanges, and ineffective information routing can make their coordination expensive. Moreover, a target model's response indicates the outcome of a test without identifying which collaboration decision should change. We present Learning to Coordinate (L2C), an LLM-guided framework that evolves an executable multi-agent workflow for each red-teaming case. L2C represents agent responsibilities, execution dependencies, and input bindings in a versioned graph, and associates each graph with records of the information actually delivered and produced. A controller trained through supervised fine-tuning integrates these records with target responses, evaluator verdicts, and remaining budget to retain the workflow, refine instructions, restructure collaboration, or lock further editing. This design connects feedback to explicit changes in subsequent execution while allowing a useful organization to continue without repeated controller intervention. The evaluation protocol covers HarmBench with three execution backbones and two target models, together with component ablations, dataset transfer, and evaluator checks. Across the six executor-target configurations, L2C improves ASR over EvoSynth by 1.4 to 4.5 percentage points while reducing mean online tokens by 35.6% to 37.3%. L2C connects adaptive collaboration to the resource requirements of automated security evaluation.
Comments: 10 pages, 3 figures
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24221 [cs.AI]
  (or arXiv:2611.24221v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.24221

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xiaoyang Xing [view email]
[v1] Wed, 18 Nov 2026 10:58:44 UTC (3,309 KB)

来源:arXiv cs.AI · arxiv.org