Imagen de Portada

Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lyu, Zongyi, Chen, Songqiang, Ji, Zhenlan, Wang, Liwen, Wang, Shuai, Wu, Daoyuan, Wang, Wenxuan, Cheung, Shing-Chi
Formato:	Preprint
Publicado:	2025
Materias:	Software Engineering Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems
por: Lyu, Zongyi, et al.
Publicado: (2026)

What Builds Effective In-Context Examples for Code Generation?
por: Li, Dongze, et al.
Publicado: (2025)

Digging Into the Internal: Causality-Based Analysis of LLM Function Calling
por: Ji, Zhenlan, et al.
Publicado: (2025)

RulER: Automated Rule-Based Semantic Error Localization and Repair for Code Translation
por: Jin, Shuo, et al.
Publicado: (2025)

Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions
por: Chen, Jingyi, et al.
Publicado: (2025)

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems
por: Wang, Liwen, et al.
Publicado: (2025)

When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?
por: Chen, Jingyi, et al.
Publicado: (2025)

Word Closure-Based Metamorphic Testing for Machine Translation
por: Xie, Xiaoyuan, et al.
Publicado: (2023)

Can Emulating Semantic Translation Help LLMs with Code Translation? A Study Based on Pseudocode
por: Chen, Songqiang, et al.
Publicado: (2025)

Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEval
por: Wu, Jiarong, et al.
Publicado: (2025)

CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit
por: Cao, Jialun, et al.
Publicado: (2024)

How Multi-Modal LLMs Reshape Visual Deep Learning Testing? A Comprehensive Study Through the Lens of Image Mutation
por: Wang, Liwen, et al.
Publicado: (2024)

Exploring Multi-Lingual Bias of Large Code Models in Code Generation
por: Wang, Chaozheng, et al.
Publicado: (2024)

MR-Adopt: Automatic Deduction of Input Transformation Function for Metamorphic Testing
por: Xu, Congying, et al.
Publicado: (2024)

MR-Coupler: Automated Metamorphic Test Generation via Functional Coupling Analysis
por: Xu, Congying, et al.
Publicado: (2026)

API-guided Dataset Synthesis to Finetune Large Code Models
por: Li, Zongjie, et al.
Publicado: (2024)

Concerned with Data Contamination? Assessing Countermeasures in Code Language Model
por: Cao, Jialun, et al.
Publicado: (2024)

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

Automatic Build Repair for Test Cases using Incompatible Java Versions
por: Mak, Ching Hang, et al.
Publicado: (2024)

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
por: Mo, Wenjie Jacky, et al.
Publicado: (2025)

AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation
por: Zhu, Yueheng, et al.
Publicado: (2025)

Scaling Coding Agents via Atomic Skills
por: Ma, Yingwei, et al.
Publicado: (2026)

A Systematic Evaluation of Large Code Models in API Suggestion: When, Which, and How
por: Wang, Chaozheng, et al.
Publicado: (2024)

Position Paper: Programming Language Techniques for Bridging LLM Code Generation Semantic Gaps
por: Du, Yalong, et al.
Publicado: (2025)

SPENCER: Self-Adaptive Model Distillation for Efficient Code Retrieval
por: Gu, Wenchao, et al.
Publicado: (2025)

Towards Understanding the Bugs in Solidity Compiler
por: Ma, Haoyang, et al.
Publicado: (2024)

Understanding and Characterizing Mock Assertions in Unit Tests
por: Zhu, Hengcheng, et al.
Publicado: (2025)

ReuseDroid: A VLM-empowered Android UI Test Migrator Boosted by Active Feedback
por: Li, Xiaolei, et al.
Publicado: (2025)

MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
por: Wang, Zhengren, et al.
Publicado: (2025)

SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization
por: Wang, Yanlin, et al.
Publicado: (2024)

DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation
por: Zhu, Qiming, et al.
Publicado: (2024)

VisCoder2: Building Multi-Language Visualization Coding Agents
por: Ni, Yuansheng, et al.
Publicado: (2025)

Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators
por: Zhang, Kunpeng, et al.
Publicado: (2025)

Rigor, Reliability, and Reproducibility Matter: A Decade-Scale Survey of 572 Code Benchmarks
por: Cao, Jialun, et al.
Publicado: (2025)

LSPFuzz: Hunting Bugs in Language Servers
por: Zhu, Hengcheng, et al.
Publicado: (2025)

Fixturize: Bridging the Fixture Gap in Test Generation
por: Wang, Chengyi, et al.
Publicado: (2026)

HyClone: Bridging LLM Understanding and Dynamic Execution for Semantic Code Clone Detection
por: Liang, Yunhao, et al.
Publicado: (2025)

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

GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
por: Liu, Wei, et al.
Publicado: (2024)

CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models
por: Yu, Hao, et al.
Publicado: (2023)