Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gezgin, Derin, Das, Amartya, Kim, Shinhae, Huang, Zhengdong, Stojkovic, Nevena, Wang, Claire
Formato:	Preprint
Publicado:	2026
Materias:	Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

From Transactions to Exploits: Automated PoC Synthesis for Real-World DeFi Attacks
por: Su, Xing, et al.
Publicado: (2026)

SmartPoC: Generating Executable and Validated PoCs for Smart Contract Bug Reports
por: Chen, Longfei, et al.
Publicado: (2025)

PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages
por: Simsek, Deniz, et al.
Publicado: (2025)

PoCo: Agentic Proof-of-Concept Exploit Generation for Smart Contracts
por: Andersson, Vivi, et al.
Publicado: (2025)

Precision or Peril: A PoC of Python Code Quality from Quantized Large Language Models
por: Melin, Eric L., et al.
Publicado: (2024)

Patch-to-PoC: A Systematic Study of Agentic LLM Systems for Linux Kernel N-Day Reproduction
por: Pu, Juefei, et al.
Publicado: (2026)

AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection
por: Zhao, Zijie, et al.
Publicado: (2026)

Program Analysis Guided LLM Agent for Proof-of-Concept Generation
por: Desai, Achintya, et al.
Publicado: (2026)

Is LLM-Generated Code More Maintainable \& Reliable than Human-Written Code?
por: Molison, Alfred Santa, et al.
Publicado: (2025)

Testing Deep Learning Libraries via Neurosymbolic Constraint Learning
por: Naziri, M M Abid, et al.
Publicado: (2026)

Towards Operation Proof Obligation Generation for VDM
por: Battle, Nick, et al.
Publicado: (2025)

EvoPoC: Automated Exploit Synthesis for DeFi Smart Contracts via Hierarchical Knowledge Graphs
por: Liang, Ruichao, et al.
Publicado: (2026)

Exploring Prompt Patterns in AI-Assisted Code Generation: Towards Faster and More Effective Developer-AI Collaboration
por: DiCuffa, Sophia, et al.
Publicado: (2025)

Multi-LLM Orchestration for High-Quality Code Generation: Exploiting Complementary Model Strengths
por: Chen, Huashan, et al.
Publicado: (2025)

LLMs in Code Vulnerability Analysis: A Proof of Concept
por: Sultana, Shaznin, et al.
Publicado: (2026)

V-GameGym: Visual Game Generation for Code Large Language Models
por: Zhang, Wei, et al.
Publicado: (2025)

A Systematic Study on Generating Web Vulnerability Proof-of-Concepts Using Large Language Models
por: Zhao, Mengyao, et al.
Publicado: (2025)

Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation
por: Sarker, Laboni, et al.
Publicado: (2024)

FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents
por: Nitin, Vikram, et al.
Publicado: (2025)

Automatic Generation of Benchmarks and Reliable LLM Judgment for Code Tasks
por: Farchi, Eitan, et al.
Publicado: (2024)

Towards a Human-in-the-Loop Framework for Reliable Patch Evaluation Using an LLM-as-a-Judge
por: Shi, Sherry, et al.
Publicado: (2025)

Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review
por: Mitropoulos, Dimitris, et al.
Publicado: (2026)

KTester: Leveraging Domain and Testing Knowledge for More Effective LLM-based Test Generation
por: Li, Anji, et al.
Publicado: (2025)

Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming
por: Chakraborty, Saikat, et al.
Publicado: (2024)

ProofWright: Towards Agentic Formal Verification of CUDA
por: Chatterjee, Bodhisatwa, et al.
Publicado: (2025)

ReqElicitGym: An Evaluation Environment for Interview Competence in Conversational Requirements Elicitation
por: Jin, Dongming, et al.
Publicado: (2026)

PBFuzz: Agentic Directed Fuzzing for PoV Generation
por: Zeng, Haochen, et al.
Publicado: (2025)

Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs
por: Yang, Ya-Ting, et al.
Publicado: (2026)

Towards a Completeness Argumentation for Scenario Concepts
por: Glasmacher, Christoph, et al.
Publicado: (2024)

Towards Reliable LLM-Driven Fuzz Testing: Vision and Road Ahead
por: Cheng, Yiran, et al.
Publicado: (2025)

Execution-State-Aware LLM Reasoning for Automated Proof-of-Vulnerability Generation
por: Li, Haoyu, et al.
Publicado: (2026)

Measuring the Unmeasurable: Markov Chain Reliability for LLM Agents
por: Tran-Truong, Phat T., et al.
Publicado: (2026)

Concept-Based Generic Programming in C++
por: Stroustrup, Bjarne
Publicado: (2025)

Enhancing LLM's Ability to Generate More Repository-Aware Unit Tests Through Precise Contextual Information Injection
por: Yin, Xin, et al.
Publicado: (2025)

LLM-Assisted Tool for Joint Generation of Formulas and Functions in Rule-Based Verification of Map Transformations
por: He, Ruidi, et al.
Publicado: (2025)

Real-World Usability of Vulnerability Proof-of-Concepts: A Comprehensive Study
por: Dang, Wenjing, et al.
Publicado: (2025)

Training Software Engineering Agents and Verifiers with SWE-Gym
por: Pan, Jiayi, et al.
Publicado: (2024)

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
por: Xie, Yiqing, et al.
Publicado: (2026)

VerifyThisBench: Generating Code, Specifications, and Proofs All at Once
por: Deng, Xun, et al.
Publicado: (2025)

LLM-Assisted Thematic Analysis: Opportunities, Limitations, and Recommendations
por: Ornelas, Tatiane, et al.
Publicado: (2025)