Hacking CTFs with Plain Agents
Authors: Rustem Turtayev, Artem Petrov, Dmitrii Volkov, Denis Volk
Abstract: We saturate a high-school-level hacking benchmark with plain LLM agent design. Concretely, we obtain 95% performance on InterCode-CTF, a popular offensive security benchmark, using prompting, tool use, and multiple attempts. This beats prior work by Phuong et al. 2024 (29%) and Abramovich et al. 2024 (72%). Our results suggest that current LLMs have surpassed the high school level in offensive cybersecurity. Their hacking capabilities remain underelicited: our ReAct&Plan prompting strategy solves many challenges in 1-2 turns without complex engineering or advanced harnessing.
Explore the paper tree
Click on the tree nodes to be redirected to a given paper and access their summaries and virtual assistant
Look for similar papers (in beta version)
By clicking on the button above, our algorithm compares the title and abstract of this paper with all the papers of the same arXiv category that we have summarized, and finds the closest ones. You can rerun it from time to time: the results improve as our database grows.