Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yongchao, Huang, Zhiqiu
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
by: Son, Ha Min, et al.
Published: (2025)

SolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete Execution
by: Lee, Woojin, et al.
Published: (2026)

DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information
by: Huang, Zhili, et al.
Published: (2025)

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
by: Li, Yuanhao, et al.
Published: (2026)

Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair
by: Cheng, Runxiang, et al.
Published: (2026)

Agentic Bug Reproduction for Effective Automated Program Repair at Google
by: Cheng, Runxiang, et al.
Published: (2025)

The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE
by: Feldt, Robert, et al.
Published: (2026)

Agentic AI Software Engineers: Programming with Trust
by: Roychoudhury, Abhik, et al.
Published: (2025)

MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair
by: Dehghan, Meghdad, et al.
Published: (2024)

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

CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation
by: Du, Kounianhua, et al.
Published: (2024)

ARISE: A Repository-level Graph Representation and Toolset for Agentic Fault Localization and Program Repair
by: Seddik, Shahd, et al.
Published: (2026)

Security Is Relative: Training-Free Vulnerability Detection via Multi-Agent Behavioral Contract Synthesis
by: Wang, Yongchao, et al.
Published: (2026)

Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
by: Garg, Spandan, et al.
Published: (2026)

Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
by: de Macedo, Sanderson Oliveira, et al.
Published: (2026)

BabelCoder: Agentic Code Translation with Specification Alignment
by: Rabbi, Fazle, et al.
Published: (2025)

Repairing Tool Calls Using Post-tool Execution Reflection and RAG
by: Tsay, Jason, et al.
Published: (2025)

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
by: Bouzenia, Islem, et al.
Published: (2024)

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

Agentic Scientific Simulation: Execution-Grounded Model Construction and Reconstruction
by: Lie, Knut-Andreas, et al.
Published: (2026)

Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents
by: Armesto, Maximiliano, et al.
Published: (2026)

RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair
by: Pan, Zhongqiang, et al.
Published: (2026)

Agentic Specification Generator for Move Programs
by: Fu, Yu-Fu, et al.
Published: (2025)

Enhancing Automated Program Repair with Solution Design
by: Zhao, Jiuang, et al.
Published: (2024)

Collaborative Agents for Automated Program Repair in Ruby
by: Akbarpour, Nikta, et al.
Published: (2025)

Evaluating Agent-based Program Repair at Google
by: Rondon, Pat, et al.
Published: (2025)

Evaluating the Generalizability of LLMs in Automated Program Repair
by: Li, Fengjie, et al.
Published: (2025)

STELP: Secure Transpilation and Execution of LLM-Generated Programs
by: Shinde, Swapnil, et al.
Published: (2026)

HAFixAgent: History-Aware Program Repair Agent
by: Shi, Yu, et al.
Published: (2025)

Multi-Task Program Error Repair and Explanatory Diagnosis
by: Xu, Zhenyu, et al.
Published: (2024)

LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation
by: Xu, Dong, et al.
Published: (2026)

SpecRover: Code Intent Extraction via LLMs
by: Ruan, Haifeng, et al.
Published: (2024)

MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
by: Liu, Simiao, et al.
Published: (2026)

You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects
by: Bouzenia, Islem, et al.
Published: (2024)

CrackMeBench: Binary Reverse Engineering for Agents
by: David, Isaac, et al.
Published: (2026)

Unveiling Project-Specific Bias in Neural Code Models
by: Li, Zhiming, et al.
Published: (2022)

Self-Bootstrapping Automated Program Repair: Using LLMs to Generate and Evaluate Synthetic Training Data for Bug Repair
by: de-Fitero-Dominguez, David, et al.
Published: (2025)

On the Role of Fault Localization Context for LLM-Based Program Repair
by: Sepidband, Melika, et al.
Published: (2026)

VeriAct: Beyond Verifiability -- Agentic Synthesis of Correct and Complete Formal Specifications
by: Misu, Md Rakib Hossain, et al.
Published: (2026)

From Benchmark Data To Applicable Program Repair: An Experience Report
by: Chandramohan, Mahinthan, et al.
Published: (2025)