# PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy

arXiv: https://arxiv.org/abs/2604.06618 · HTML: https://mlsanity.com/paper/2604.06618/

## Key facts

- Cited by 1 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 21 of its 43 references that are in the map.
- First posted on arXiv 8 Apr 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, 21 of 21)

- [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)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [PentestGPT: An LLM-empowered Automatic Penetration Testing Tool](https://mlsanity.com/paper/2308.06782/) (2023)
- [From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs](https://mlsanity.com/paper/2509.01835/) (2025)
- [PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages](https://mlsanity.com/paper/2506.04962/) (2025)
- [FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents](https://mlsanity.com/paper/2507.15241/) (2025)
- [What Makes a Good LLM Agent for Real-world Penetration Testing?](https://mlsanity.com/paper/2602.17622/) (2026)
- [VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection](https://mlsanity.com/paper/2509.11523/) (2025)
- [PoCo: Agentic Proof-of-Concept Exploit Generation for Smart Contracts](https://mlsanity.com/paper/2511.02780/) (2025)
- [Patch-to-PoC: A Systematic Study of Agentic LLM Systems for Linux Kernel N-Day Reproduction](https://mlsanity.com/paper/2602.07287/) (2026)
- [A Systematic Study on Generating Web Vulnerability Proof-of-Concepts Using Large Language Models](https://mlsanity.com/paper/2510.10148/) (2025)
- [SmartPoC: Generating Executable and Validated PoCs for Smart Contract Bug Reports](https://mlsanity.com/paper/2511.12993/) (2025)
- [Survey of Automated Vulnerability Detection and Exploit Generation Techniques in Cyber Reasoning Systems](https://mlsanity.com/paper/1702.06162/) (2017)
- [A Systematic Literature Review on Automated Exploit and Security Test Generation](https://mlsanity.com/paper/2502.04953/) (2025)
- [Survey of Methods for Automated Code-Reuse Exploit Generation](https://mlsanity.com/paper/2011.07862/) (2020)

## Built on by (most cited first, 1 of 1)

- [From Runnable to Verifiable: An Independent Reproducibility Study of LLM/Agent-Driven Vulnerability Validation Artifacts](https://mlsanity.com/paper/2608.09567/) (2026)

## Abstract (arXiv)

While recent approaches leverage large language models (LLMs) and multi-agent pipelines to automatically generate proof-of-concept (PoC) exploits from vulnerability reports, existing systems often suffer from two fundamental limitations: unreliable validation based on surface-level execution signals and high operational cost caused by extensive trial-and-error during exploit generation. In this paper, we present PoC-Adapt, an end-to-end framework for automated PoC generation and verification, architected upon a foundation semantic runtime validation and adaptive policy learning. At the core of PoC-Adapt is a Semantic Oracle that validates exploits by comparing structured pre- and post-execution system states, enabling reliable distinction between true vulnerability exploitation and incidental behavioral changes. To reduce exploration cost, we further introduce an Adaptive Policy Learning mechanism that learns an exploitation policy over semantic states and actions, guiding the exploit agent toward effective strategies with fewer failed attempts. PoC-Adapt is implemented as a multi-agent system comprising specialized agents for root cause analysis, environment building, exploit generation, and semantic validation, coordinated through structured feedback loops. Experimenting on the CWE-Bench-Java and PrimeVul benchmarks shows that PoC-Adapt significantly improves verification reliability by 25% and reduces exploit generation cost compared to prior LLM-based systems, highlighting the importance of semantic validation and learned action policies in automated vulnerability reproduction. Applied to the latest CVE corpus, PoC-Adapt confirmed 12 verified PoC out of 80 reproduce attempts at a cost of 0.42 per generated exploit