Copertina

Review Beats Planning: Dual-Model Interaction Patterns for Code Synthesis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Miller, Jan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering D.2.5; I.2.2
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Specification as Quality Gate: Three Hypotheses on AI-Assisted Code Review
di: Zietsman, Christo
Pubblicazione: (2026)

RelRepair: Enhancing Automated Program Repair by Retrieving Relevant Code
di: Liu, Shunyu, et al.
Pubblicazione: (2025)

Runtime Execution Traces Guided Automated Program Repair with Multi-Agent Debate
di: Wu, Jiaqing, et al.
Pubblicazione: (2026)

Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair
di: Cambronero, José, et al.
Pubblicazione: (2025)

CIFE: Code Instruction-Following Evaluation
di: Gunnu, Sravani, et al.
Pubblicazione: (2025)

AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs
di: Ahmed, Sheikh Nazib, et al.
Pubblicazione: (2026)

Multi-Agent Code Verification via Information Theory
di: Rajan, Shreshth
Pubblicazione: (2025)

CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement
di: Borra, Ajay Krishna, et al.
Pubblicazione: (2026)

Addressing Data Leakage in HumanEval Using Combinatorial Test Design
di: Bradbury, Jeremy S., et al.
Pubblicazione: (2024)

Experience with GitHub Copilot for Developer Productivity at Zoominfo
di: Bakal, Gal, et al.
Pubblicazione: (2025)

Validating Solidity Code Defects using Symbolic and Concrete Execution powered by Large Language Models
di: Susan, Ştefan-Claudiu, et al.
Pubblicazione: (2025)

LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops
di: Ravi, Ravin, et al.
Pubblicazione: (2026)

It's Alive! What a Live Object Environment Changes in Software Engineering Practice
di: Grigera, Julián, et al.
Pubblicazione: (2026)

Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications
di: Rehan, Tzafrir
Pubblicazione: (2026)

SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair
di: Dinu, Ion George, et al.
Pubblicazione: (2026)

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

COMET: Coverage-guided Model Generation For Deep Learning Library Testing
di: Li, Meiziniu, et al.
Pubblicazione: (2022)

The Right Prompts for the Job: Repair Code-Review Defects with Large Language Model
di: Zhao, Zelin, et al.
Pubblicazione: (2023)

SpecOps: A Fully Automated AI Agent Testing Framework in Real-World GUI Environments
di: Ahmed, Syed Yusuf, et al.
Pubblicazione: (2026)

VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs
di: Daneshvar, Seyed Shayan, et al.
Pubblicazione: (2024)

MeDeT: Medical Device Digital Twins Creation with Few-shot Meta-learning
di: Sartaj, Hassan, et al.
Pubblicazione: (2024)

Adaptive and AI-Augmented Security Testing: A Systematic Survey of Program Analysis, Feedback-Driven Testing, and Hybrid Learning-Based Approaches
di: Wienczkowski, Michael
Pubblicazione: (2026)

TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
di: Alonso, Pepe, et al.
Pubblicazione: (2026)

Code Documentation and Analysis to Secure Software Development
di: Attie, Paul, et al.
Pubblicazione: (2024)

Demystifying the Silence of Correctness Bugs in PyTorch Compiler
di: Li, Meiziniu, et al.
Pubblicazione: (2026)

Enhancing Differential Testing With LLMs For Testing Deep Learning Libraries
di: Li, Meiziniu, et al.
Pubblicazione: (2024)

Proof of Concept as a First-Class Architectural Decision Instrument
di: Antognolli, Bruno Fernando, et al.
Pubblicazione: (2026)

Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code
di: Haseeb, Muhammad
Pubblicazione: (2025)

Orion: Fuzzing Workflow Automation
di: Bazalii, Max, et al.
Pubblicazione: (2025)

AddressWatcher: Sanitizer-Based Localization of Memory Leak Fixes
di: Murali, Aniruddhan, et al.
Pubblicazione: (2024)

Understanding and Detecting Flaky Builds in GitHub Actions
di: Ge, Wenhao, et al.
Pubblicazione: (2026)

Scattered Forest Search: Smarter Code Space Exploration with LLMs
di: Light, Jonathan, et al.
Pubblicazione: (2024)

L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
di: Holt, Samuel, et al.
Pubblicazione: (2023)

Utilizing Precise and Complete Code Context to Guide LLM in Automatic False Positive Mitigation
di: Chen, Jinbao, et al.
Pubblicazione: (2024)

CodeTracer: Towards Traceable Agent States
di: Li, Han, et al.
Pubblicazione: (2026)

Context-Augmented Code Generation: How Product Context Improves AI Coding Agent Decision Compliance by 49%
di: Dillon, Drew, et al.
Pubblicazione: (2026)

AIRA: AI-Induced Risk Audit: A Structured Inspection Framework for AI-Generated Code
di: Parris, William M.
Pubblicazione: (2026)

Kajal: Extracting Grammar of a Source Code Using Large Language Models
di: Torkamani, Mohammad Jalili
Pubblicazione: (2024)

CASCADE: Detecting Inconsistencies between Code and Documentation with Automatic Test Generation
di: Kiecker, Tobias, et al.
Pubblicazione: (2026)

DeepCodeProbe: Towards Understanding What Models Trained on Code Learn
di: Majdinasab, Vahid, et al.
Pubblicazione: (2024)