cs.AINov 18, 2026

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

Authors: Xiaoyang Xing, Wenyu Dai, Xiaoliang Gong, Asoke K Nandi, Anthony Cohn

Organizations: School of Computer Science and Technology, Tongji University, Shanghai, China · Electronic and Electrical Engineering, Brunel University of London, Uxbridge, UK · School of Computer Science, University of Leeds, Leeds, UK

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.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. There are Levels to It: Red Teaming Dialogue With Hierarchical Reinforcement Learning

    Aug 6, 2025Roman Belaire, Arunesh Sinha, Pradeep VarakanthamLLM Red TeamingAdversarial Attacks on LLMs

  2. Adaptive Instruction Composition for Automated LLM Red-Teaming

    Apr 22, 2026Jesse Zymet, Andy Luo, Swapnil Shinde +2Adversarial Prompt GenerationLLM Red Teaming