Image de couverture de livre

Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cambronero, José, Tufano, Michele, Shi, Sherry, Wei, Renyao, Uy, Grant, Cheng, Runxiang, Liu, Chin-Jung, Pan, Shiying, Chandra, Satish, Rondon, Pat
Format:	Preprint
Publié:	2025
Sujets:	Software Engineering Artificial Intelligence D.2.5; I.2.2
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

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)

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

Towards a Human-in-the-Loop Framework for Reliable Patch Evaluation Using an LLM-as-a-Judge
par: Shi, Sherry, et autres
Publié: (2025)

Towards Verified Code Reasoning by LLMs
par: Sistla, Meghana, et autres
Publié: (2025)

RelRepair: Enhancing Automated Program Repair by Retrieving Relevant Code
par: Liu, Shunyu, et autres
Publié: (2025)

Tool Forge: A Validation-Carrying Toolchain for Governed Agentic Execution
par: Rao, Swanand
Publié: (2026)

Clover: A Neural-Symbolic Agentic Harness with Stochastic Tree-of-Thoughts for Verified RTL Repair
par: Luo, Zizhang, et autres
Publié: (2026)

DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models
par: Yuan, Mingyue, et autres
Publié: (2024)

Runtime Execution Traces Guided Automated Program Repair with Multi-Agent Debate
par: Wu, Jiaqing, et autres
Publié: (2026)

Overhead Measurement Noise in Different Runtime Environments
par: Reichelt, David Georg, et autres
Publié: (2024)

Dynamic Dual-Granularity Skill Bank for Agentic RL
par: Tu, Songjun, et autres
Publié: (2026)

How much does AI impact development speed? An enterprise-based randomized controlled trial
par: Paradis, Elise, et autres
Publié: (2024)

REPOT: Recoverable Program-of-Thought via Checkpoint Repair
par: Mazaheri, Parsa
Publié: (2026)

Causality-Driven Neural Network Repair: Challenges and Opportunities
par: Vares, Fatemeh, et autres
Publié: (2025)

SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair
par: Dinu, Ion George, et autres
Publié: (2026)

Hydrodynamic simulation of urban stormwater drain (Delhi city, India) using iRIC Model
par: Satish Kumar
Publié: (2018)

Physics-Informed Policy Optimization via Analytic Dynamics Regularization
par: Chandra, Namai, et autres
Publié: (2026)

eStonefish-Scenes: A Sim-to-Real Validated and Robot-Centric Event-based Optical Flow Dataset for Underwater Vehicles
par: Mansour, Jad, et autres
Publié: (2025)

GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair
par: Liu, Zhuoyao, et autres
Publié: (2026)

AgenticTyper: Automated Typing of Legacy Software Projects Using Agentic AI
par: Pohle, Clemens
Publié: (2026)

An Agentic Framework for Neuro-Symbolic Programming
par: Nafar, Aliakbar, et autres
Publié: (2026)

TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
par: Alonso, Pepe, et autres
Publié: (2026)

AI-assisted 3D Preservation and Reconstruction of Temple Arts
par: Shih, Naai-Jung
Publié: (2025)

Fibonacci and Lucas Sequences in Aperiodic Monotile Supertiles
par: Dong, Shiying
Publié: (2024)

Partially Observable Reference Policy Programming: Solving POMDPs Sans Numerical Optimisation
par: Kim, Edward, et autres
Publié: (2025)

AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair
par: Hu, Yuelin, et autres
Publié: (2026)

Front-door Reducibility: Reducing ADMGs to the Standard Front-door Setting via a Graphical Criterion
par: Mao, Jianqiao, et autres
Publié: (2025)

Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems
par: Nath, Saptarshi, et autres
Publié: (2025)

CodeCompass: Navigating the Navigation Paradox in Agentic Code Intelligence
par: Paipuru, Tarakanath
Publié: (2026)

AAFLOW: Scalable Patterns for Agentic AI Workflows
par: Sarker, Arup Kumar, et autres
Publié: (2026)

Aligning Validation with Deployment in Spatial Prediction: Target-Weighted Cross-Validation
par: Brenning, Alexander, et autres
Publié: (2026)

Domain-Independent Dynamic Programming
par: Kuroiwa, Ryo, et autres
Publié: (2024)

Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design
par: Yamada, Masaru
Publié: (2026)

Trace Validation of Unmodified Concurrent Systems with OmniLink
par: Hackett, Finn, et autres
Publié: (2026)

Síntesis, caracterización y actividad catalítica de MoS2/MCM-48 en la hidrodesulfuración de dibenzotiofeno
par: Jairo Rondón
Publié: (2016)

Monitoring Agentic Systems Before They're Reliable
par: Boston, Marisa Ferrara, et autres
Publié: (2026)

Deployment-Time Reliability of Learned Robot Policies
par: Agia, Christopher
Publié: (2026)

Policy-Grounded Safety Evaluation of 20 Large Language Models
par: Contreras, Juan Manuel
Publié: (2025)

Decision Evidence Maturity Model for Agentic AI: A Property-Level Method Specification
par: Solozobov, Oleg
Publié: (2026)