Skip to content
#small language model Open access

Pwnagent: a knowledge-guided multi-agent system for automatic exploit generation

Sep 2026 · Cybersecurity · Vol 9 · 0 citations · 47 references

TL;DR

PwnAgent, an LLM-driven multi-agent framework for end-to-end exploit generation that combines offensive domain knowledge with active runtime introspection, is presented and paired results indicate that structured knowledge guidance, execution-grounded measurement, and feedback repair improve LLM-based exploit generation in the evaluated setting.

Abstract

Automatic Exploit Generation (AEG) plays an important role in proactive assessment of software threats by identifying vulnerabilities and constructing functional payloads. Existing Large Language Model (LLM)-based methods, however, often struggle to reason about complex exploit logic and to perform runtime introspection, leaving a gap between static vulnerability analysis and dynamic memory behavior. We present PwnAgent, an LLM-driven multi-agent framework for end-to-end exploit generation that combines offensive domain knowledge with active runtime introspection. PwnAgent uses a hierarchical knowledge base for multi-stage exploit reasoning and a feedback-driven self-correction engine to calibrate dynamic memory parameters during execution. Because broad Capture The Flag (CTF) benchmarks offer limited binary-exploitation depth and pwn-specific evaluation must balance reproducibility, difficulty progression, and exploit diversity, we construct a 66-task pwn benchmark from public CTF-style challenges. The benchmark is primarily composed of Linux x86/x86-64 ELF binaries and stack-oriented tasks, with smaller format-string, heap, integer-overflow, ARM, and MIPS subsets used as limited probes beyond the dominant setting. Under the same recent Kimi-K2.6 backend, PwnAgent achieves a 62.12% end-to-end success rate, compared with 31.82% for the evaluated PwnGPT baseline, a 30.30 percentage-point gain. These paired results indicate that structured knowledge guidance, execution-grounded measurement, and feedback repair improve LLM-based exploit generation in the evaluated setting, while the absolute success rate shows that fully autonomous exploitation remains challenging.

Read PDF

Similar papers

Preprint Sep 2026

PrimSynth: An Agentic Approach to Discover, Validate, and Synthesize Exploit Primitives for Linux Kernel Vulnerabilities

Linux kernel vulnerabilities are critical to downstream systems. Despite extensive research on automated kernel exploitation, a fundamental challenge remains the conceptual gap between abstract exploit strategies and concrete technical operations. To fill this gap, this paper introduces a systematic characterization th...

Pengfei Wang, Anthea Chen, Dan-Jun Liu et al. · 0 citations
Preprint Aug 2026

A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks

This work proposes a self-evolving test-time defense built around a persistent, cross-interaction rule memory that substantially reduces attack success rates while preserving benign utility, remains robust under an adaptive composite-wrapper attack, and does not increase over-refusal as the memory grows.

Tongshen Hu, Bryan Hooi · 0 citations
#artificial intelligence Preprint Oct 2026

EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents

Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources. Existing benchmarks leave gaps in executable coverage of their runtime security risks, while evolving model capabilities, harnesses, tools, and threats motivate benchma...

Shi Kuang, Xue-Mei Luo, Kun Liu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

SelfOp: An Optimization Algorithm for Self-Improving Security Agents

LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and patch generation. Improving them at the model level demands expert demonstrations or computable rewards, which security tasks rarely offer: traces are costly, failures hard to diagnose, rewards sparse, and non-comput...

Saad Ullah, Yiğitcan Kaya, Christopher Kruegel et al. · 0 citations
Conference Open access Sep 2026

PENTESTLLMAGENT: A Task Dependency Graph Planning-Based Multi-Agent Framework for Automated Penetration Testing

PentestLLMAgent is proposed, which integrates a Task Dependency Graph (TDG) for dynamic planning and backtracking; a Hierarchical Multi-Agent Architecture (HMA) with function-calling-based tool invocation, output filtering, and semantic compression, and Executable Knowledge-Guided Command Generation (EKG-CG) for retrie...

Shuo Sheng, Jixin Zhang, Jia Yang et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.