# Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

arXiv: https://arxiv.org/abs/2406.01637 · HTML: https://mlsanity.com/paper/2406.01637/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 70 references that are in the map.
- First posted on arXiv 2 Jun 2024.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models](https://mlsanity.com/paper/2310.02949/) (2023)
- [Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks](https://mlsanity.com/paper/2302.05733/) (2023)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [TALM: Tool Augmented Language Models](https://mlsanity.com/paper/2205.12255/) (2022)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [Removing RLHF Protections in GPT-4 via Fine-Tuning](https://mlsanity.com/paper/2311.05553/) (2023)
- [Chain of Hindsight Aligns Language Models with Feedback](https://mlsanity.com/paper/2302.02676/) (2023)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [LLM Agents can Autonomously Exploit One-day Vulnerabilities](https://mlsanity.com/paper/2404.08144/) (2024)
- [LLM Agents can Autonomously Hack Websites](https://mlsanity.com/paper/2402.06664/) (2024)
- [Getting pwn'd by AI: Penetration Testing with Large Language Models](https://mlsanity.com/paper/2308.00121/) (2023)
- [MACRec: a Multi-Agent Collaboration Framework for Recommendation](https://mlsanity.com/paper/2402.15235/) (2024)
- [Holistic Safety and Responsibility Evaluations of Advanced AI Models](https://mlsanity.com/paper/2404.14068/) (2024)
- [Will AI Make Cyber Swords or Shields: A few mathematical models of technological progress](https://mlsanity.com/paper/2207.13825/) (2022)

## Built on by (most cited first, 30 of 95)

- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities](https://mlsanity.com/paper/2503.17332/) (2025)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents](https://mlsanity.com/paper/2410.13886/) (2024)
- [VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2501.13411/) (2025)
- [Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents](https://mlsanity.com/paper/2602.13379/) (2026)
- [A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents](https://mlsanity.com/paper/2506.23844/) (2025)
- [AutoPenBench: Benchmarking Generative Agents for Penetration Testing](https://mlsanity.com/paper/2410.03225/) (2024)
- [Frontier AI's Impact on the Cybersecurity Landscape](https://mlsanity.com/paper/2504.05408/) (2025)
- [A Survey on Agentic Security: Applications, Threats and Defenses](https://mlsanity.com/paper/2510.06445/) (2025)
- [SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills](https://mlsanity.com/paper/2604.06550/) (2026)
- [Estimating Worst-Case Frontier Risks of Open-Weight LLMs](https://mlsanity.com/paper/2508.03153/) (2025)
- [Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents](https://mlsanity.com/paper/2607.10487/) (2026)
- [Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks](https://mlsanity.com/paper/2501.16466/) (2025)
- [Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks](https://mlsanity.com/paper/2410.20911/) (2024)
- [The AI Agent Index](https://mlsanity.com/paper/2502.01635/) (2025)
- [Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges](https://mlsanity.com/paper/2506.17644/) (2025)
- [Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing](https://mlsanity.com/paper/2512.09882/) (2025)
- [Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Design](https://mlsanity.com/paper/2504.10112/) (2025)
- [Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios](https://mlsanity.com/paper/2603.11214/) (2026)
- [Synthesizing Multi-Agent Harnesses for Vulnerability Discovery](https://mlsanity.com/paper/2604.20801/) (2026)
- [Seven Security Challenges in Cross-domain Multi-agent LLM Systems](https://mlsanity.com/paper/2505.23847/) (2025)
- [FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents](https://mlsanity.com/paper/2507.15241/) (2025)
- [Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements](https://mlsanity.com/paper/2410.17141/) (2024)
- [A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework](https://mlsanity.com/paper/2604.23338/) (2026)
- [AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents](https://mlsanity.com/paper/2505.10321/) (2025)
- [Security Analysis of Agentic AI Communication Protocols: A Comparative Evaluation](https://mlsanity.com/paper/2511.03841/) (2025)
- [Dynamic Risk Assessments for Offensive Cybersecurity Agents](https://mlsanity.com/paper/2505.18384/) (2025)
- [Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance](https://mlsanity.com/paper/2603.19974/) (2026)
- [A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares](https://mlsanity.com/paper/2408.05061/) (2024)

## Abstract (arXiv)

LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when given a description of the vulnerability and toy capture-the-flag problems. However, these agents still perform poorly on real-world vulnerabilities that are unknown to the agent ahead of time (zero-day vulnerabilities). In this work, we show that teams of LLM agents can exploit real-world, zero-day vulnerabilities. Prior agents struggle with exploring many different vulnerabilities and long-range planning when used alone. To resolve this, we introduce HPTSA, a system of agents with a planning agent that can launch subagents. The planning agent explores the system and determines which subagents to call, resolving long-term planning issues when trying different vulnerabilities. We construct a benchmark of 14 real-world vulnerabilities and show that our team of agents improve over prior agent frameworks by up to 4.3X.