Image de couverture de livre

Project Prometheus: Bridging the Intent Gap in Agentic Program Repair via Reverse-Engineered Executable Specifications

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Yongchao, Huang, Zhiqiu
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
par: Son, Ha Min, et autres
Publié: (2025)

SolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete Execution
par: Lee, Woojin, et autres
Publié: (2026)

DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information
par: Huang, Zhili, et autres
Publié: (2025)

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
par: Li, Yuanhao, et autres
Publié: (2026)

Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair
par: Cheng, Runxiang, et autres
Publié: (2026)

Agentic Bug Reproduction for Effective Automated Program Repair at Google
par: Cheng, Runxiang, et autres
Publié: (2025)

The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE
par: Feldt, Robert, et autres
Publié: (2026)

Agentic AI Software Engineers: Programming with Trust
par: Roychoudhury, Abhik, et autres
Publié: (2025)

MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair
par: Dehghan, Meghdad, et autres
Publié: (2024)

From Code-Centric to Intent-Centric Software Engineering: A Reflexive Thematic Analysis of Generative AI, Agentic Systems, and Engineering Accountability
par: De La Cruz, Elyson
Publié: (2026)

CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation
par: Du, Kounianhua, et autres
Publié: (2024)

ARISE: A Repository-level Graph Representation and Toolset for Agentic Fault Localization and Program Repair
par: Seddik, Shahd, et autres
Publié: (2026)

Security Is Relative: Training-Free Vulnerability Detection via Multi-Agent Behavioral Contract Synthesis
par: Wang, Yongchao, et autres
Publié: (2026)

Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
par: Garg, Spandan, et autres
Publié: (2026)

Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
par: de Macedo, Sanderson Oliveira, et autres
Publié: (2026)

BabelCoder: Agentic Code Translation with Specification Alignment
par: Rabbi, Fazle, et autres
Publié: (2025)

Repairing Tool Calls Using Post-tool Execution Reflection and RAG
par: Tsay, Jason, et autres
Publié: (2025)

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
par: Bouzenia, Islem, et autres
Publié: (2024)

Quantifying the Expectation-Realisation Gap for Agentic AI Systems
par: Lobentanzer, Sebastian
Publié: (2026)

Agentic Scientific Simulation: Execution-Grounded Model Construction and Reconstruction
par: Lie, Knut-Andreas, et autres
Publié: (2026)

Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents
par: Armesto, Maximiliano, et autres
Publié: (2026)

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair
par: Pan, Zhongqiang, et autres
Publié: (2026)

Agentic Specification Generator for Move Programs
par: Fu, Yu-Fu, et autres
Publié: (2025)

Enhancing Automated Program Repair with Solution Design
par: Zhao, Jiuang, et autres
Publié: (2024)

Collaborative Agents for Automated Program Repair in Ruby
par: Akbarpour, Nikta, et autres
Publié: (2025)

Evaluating Agent-based Program Repair at Google
par: Rondon, Pat, et autres
Publié: (2025)

Evaluating the Generalizability of LLMs in Automated Program Repair
par: Li, Fengjie, et autres
Publié: (2025)

STELP: Secure Transpilation and Execution of LLM-Generated Programs
par: Shinde, Swapnil, et autres
Publié: (2026)

HAFixAgent: History-Aware Program Repair Agent
par: Shi, Yu, et autres
Publié: (2025)

Multi-Task Program Error Repair and Explanatory Diagnosis
par: Xu, Zhenyu, et autres
Publié: (2024)

LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation
par: Xu, Dong, et autres
Publié: (2026)

SpecRover: Code Intent Extraction via LLMs
par: Ruan, Haifeng, et autres
Publié: (2024)

MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
par: Liu, Simiao, et autres
Publié: (2026)

You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects
par: Bouzenia, Islem, et autres
Publié: (2024)

CrackMeBench: Binary Reverse Engineering for Agents
par: David, Isaac, et autres
Publié: (2026)

Unveiling Project-Specific Bias in Neural Code Models
par: Li, Zhiming, et autres
Publié: (2022)

Self-Bootstrapping Automated Program Repair: Using LLMs to Generate and Evaluate Synthetic Training Data for Bug Repair
par: de-Fitero-Dominguez, David, et autres
Publié: (2025)

On the Role of Fault Localization Context for LLM-Based Program Repair
par: Sepidband, Melika, et autres
Publié: (2026)

VeriAct: Beyond Verifiability -- Agentic Synthesis of Correct and Complete Formal Specifications
par: Misu, Md Rakib Hossain, et autres
Publié: (2026)

From Benchmark Data To Applicable Program Repair: An Experience Report
par: Chandramohan, Mahinthan, et autres
Publié: (2025)