# From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

arXiv: https://arxiv.org/abs/2605.10834 · HTML: https://mlsanity.com/paper/2605.10834/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 43 of its 48 references that are in the map.
- First posted on arXiv 11 May 2026.

## 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, 30 of 43)

- [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)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models](https://mlsanity.com/paper/2408.08926/) (2024)
- [MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning](https://mlsanity.com/paper/2205.00445/) (2022)
- [The Benchmark Lottery](https://mlsanity.com/paper/2107.07002/) (2021)
- [WebCanvas: Benchmarking Web Agents in Online Environments](https://mlsanity.com/paper/2406.12373/) (2024)
- [CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities](https://mlsanity.com/paper/2503.17332/) (2025)
- [NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security](https://mlsanity.com/paper/2406.05590/) (2024)
- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale](https://mlsanity.com/paper/2506.02548/) (2025)
- [PentestAgent: Incorporating LLM Agents to Automated Penetration Testing](https://mlsanity.com/paper/2411.05185/) (2024)
- [Toward an Evaluation Science for Generative AI Systems](https://mlsanity.com/paper/2503.05336/) (2025)
- [BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems](https://mlsanity.com/paper/2505.15216/) (2025)
- [HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing](https://mlsanity.com/paper/2412.01778/) (2024)
- [VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2501.13411/) (2025)

## Abstract (arXiv)

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code execution, exploit reproduction, or trajectory similarity, in simplified or narrow settings. These tools are valuable for measuring bounded capabilities, yet they do not adequately capture the complexity, open-ended exploration, and strategic decision-making required in realistic pentesting. In this paper, we present a practical evaluation protocol that shifts assessment from task completion to validated vulnerability discovery, allowing evaluation in sufficiently complex targets spanning multiple attack surfaces and vulnerability classes. The protocol combines structured ground-truth with LLM-based semantic matching to identify vulnerabilities, bipartite resolution to score findings under realistic ambiguity, continuous ground-truth maintenance, repeated and cumulative evaluation of stochastic agents, efficiency metrics, and reduced-suite selection for sustainable experimentation. This protocol extends the state of the art by enabling a more realistic, operationally informative comparison of AI pentesting agents. To enable reproducibility, we also release expert-annotated ground truth and code for the proposed evaluation protocol: https://github.com/ethiack/ethibench.