# PoC-Gym: Towards More Reliable LLM-Assisted Proof-of-Concept Exploit Generation

arXiv: https://arxiv.org/abs/2602.04165 · HTML: https://mlsanity.com/paper/2602.04165/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2026.

## Built on by (most cited first, 2 of 2)

- [WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses](https://mlsanity.com/paper/2609.36635/) (2026)
- [P2Patch: Exploit-Guided Vulnerability Repair](https://mlsanity.com/paper/2610.20245/) (2026)

## Abstract (arXiv)

Recently Large Language Models (LLMs) have been used in security-related tasks, including generating proof-of-concept (PoC) exploits. Several LLM-assisted approaches have been proposed; they typically generate PoCs from vulnerability descriptions and use additional guidance. But, such approaches are often ineffective because the signals-such as printed markers, generated files, or runtime side effects-that they use for validation may not imply that the vulnerability is triggered. Research for more reliable PoC generation is in need but yet remains challenging. We propose PoC-Gym, a pipeline for LLM-based PoC generation for Java security vulnerabilities. PoC-Gym uses both static and dynamic information, e.g., CVE-tailored prompts, static traces, and coverage-based feedback, and iteratively generates PoC candidates. Each candidate goes through a series of validations: whether the execution is complete, manifests a success signal, and reaches the sink of the target trace. We evaluate PoC-Gym using 20 Java CVEs. Across 338 runs, 116 candidates pass PoC-Gym's runtime validation and 65 candidates pass post-hoc validation against the ground-truth vulnerable locations, covering 12 of the 20 CVEs. On the 14-CVE overlap with FaultLine, the strongest PoC-Gym configuration is post-hoc valid for 8 CVEs, while FaultLine reports success for 5 CVEs under its original evaluation criterion. But, given the complexity of PoC generation, PoC-Gym also generates many runtime-valid but post-hoc-invalid PoCs. To better understand how to achieve more reliable PoC generation, we present an in-depth analysis of such PoCs and identify common sources of failures. We believe that our work provides insights for future research.