RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution

arXiv:2608.27439 · cs.CR, cs.AI · Submitted 2026-08-27 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-08-27

Updated: 2026-09-06

Terminology

• Benchmark — 8× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Agent Security Bench — 3× in this paper
• Agent Skills — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Selection Bias — 2× in this paper · explained in 4 episodes
• Zero-Shot Transfer — 2× in this paper · explained in 4 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
• The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
• JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
• Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
• Genesis: Evolving Attack Strategies for LLM Web Agent Red-Teaming
• Universal and Transferable Adversarial Attacks on Aligned Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs