# Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation

arXiv: https://arxiv.org/abs/2602.13574 · HTML: https://mlsanity.com/paper/2602.13574/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 22 of its 58 references that are in the map.
- First posted on arXiv 14 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 22 of 22)

- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities](https://mlsanity.com/paper/2503.17332/) (2025)
- [Teams of LLM Agents can Exploit Zero-Day Vulnerabilities](https://mlsanity.com/paper/2406.01637/) (2024)
- [SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks](https://mlsanity.com/paper/2506.11791/) (2025)
- [FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents](https://mlsanity.com/paper/2406.14884/) (2024)
- [Otter: Generating Tests from Issues to Validate SWE Patches](https://mlsanity.com/paper/2502.05368/) (2025)
- [Agentic Bug Reproduction for Effective Automated Program Repair at Google](https://mlsanity.com/paper/2502.01821/) (2025)
- [FlowAgent: Achieving Compliance and Flexibility for Workflow Agents](https://mlsanity.com/paper/2502.14345/) (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)
- [TestForge: Feedback-Driven, Agentic Test Suite Generation](https://mlsanity.com/paper/2503.14713/) (2025)
- [ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System](https://mlsanity.com/paper/2509.14589/) (2025)
- [SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned](https://mlsanity.com/paper/2602.07666/) (2026)
- [All You Need Is A Fuzzing Brain: An LLM-Powered System for Automated Vulnerability Detection and Patching](https://mlsanity.com/paper/2509.07225/) (2025)
- [LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?](https://mlsanity.com/paper/2510.14700/) (2025)
- [HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines](https://mlsanity.com/paper/2512.03420/) (2025)
- [PBFuzz: Agentic Directed Fuzzing for PoV Generation](https://mlsanity.com/paper/2512.04611/) (2025)
- [Fuzzing: Randomness? Reasoning! Efficient Directed Fuzzing via Large Language Models](https://mlsanity.com/paper/2507.22065/) (2025)
- [Attention Distance: A Novel Metric for Directed Fuzzing with Large Language Models](https://mlsanity.com/paper/2512.19758/) (2025)
- [ColorGo: Directed Concolic Execution](https://mlsanity.com/paper/2505.21130/) (2025)
- [AFLGopher: Accelerating Directed Fuzzing via Feasibility-Aware Guidance](https://mlsanity.com/paper/2511.10828/) (2025)

## Built on by (most cited first, 3 of 3)

- [SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?](https://mlsanity.com/paper/2605.26548/) (2026)
- [FORGE: Multi-Agent Graduated Exploitation and Detection Engineering](https://mlsanity.com/paper/2606.03453/) (2026)
- [Plug 'n' Pray: Agentic LLM-based Detection of Potential Log File Exposures in Third-Party Content Management System Plugins](https://mlsanity.com/paper/2609.17164/) (2026)

## Abstract (arXiv)

Proof-of-Vulnerability (PoV) generation is a critical task in software security, serving as a cornerstone for vulnerability validation, false positive reduction, and patch verification. While directed fuzzing effectively drives path exploration, satisfying complex semantic constraints remains a persistent bottleneck in automated exploit generation. Large Language Models (LLMs) offer a promising alternative with their semantic reasoning capabilities; however, existing LLM-based approaches lack sufficient grounding in concrete execution behavior, limiting their ability to generate precise PoVs. In this paper, we present DrillAgent, an agentic framework that reformulates PoV generation as an iterative hypothesis-verification-refinement process. To bridge the gap between static reasoning and dynamic execution, DrillAgent synergizes LLM-based semantic inference with feedback from concrete program states. The agent analyzes the target code to hypothesize inputs, observes execution behavior, and employs a novel mechanism to translate low-level execution traces into source-level constraints. This closed-loop design enables the agent to incrementally align its input generation with the precise requirements of the vulnerability. We evaluate DrillAgent on SEC-bench, a large-scale benchmark of real-world C/C++ vulnerabilities. Experimental results show that DrillAgent substantially outperforms state-of-the-art LLM agent baselines under fixed budget constraints, solving up to 52.8% more CVE tasks than the best-performing baseline. These results highlight the necessity of execution-state-aware reasoning for reliable PoV generation in complex software systems.