Cover Image

Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ashrafi, Nazmus, Bouktif, Salah, Mediani, Mohammed
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
by: Ashrafi, Nazmus
Published: (2026)

Improving Code Reviewer Recommendation: Accuracy, Latency, Workload, and Bystanders
by: Rigby, Peter C., et al.
Published: (2023)

DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education
by: Fu, Lingyue, et al.
Published: (2025)

Multi-Agent Code-Orchestrated Generation for Reliable Infrastructure-as-Code
by: Khan, Rana Nameer Hussain, et al.
Published: (2025)

CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
by: Islam, Md. Ashraful, et al.
Published: (2025)

Structural Verification for Reliable EDA Code Generation without Tool-in-the-Loop Debugging
by: Jayasuriya, Dinithi, et al.
Published: (2026)

TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code
by: Huang, Jiangping, et al.
Published: (2026)

DebugRepair: Enhancing LLM-Based Automated Program Repair via Self-Directed Debugging
by: Wu, Linhao, et al.
Published: (2026)

Debugging Performance Issues in WebAssembly Runtimes via Mutation-based Inference
by: Zeng, Ruiying, et al.
Published: (2026)

Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision
by: Lu, Xu, et al.
Published: (2025)

Leveraging Print Debugging to Improve Code Generation in Large Language Models
by: Hu, Xueyu, et al.
Published: (2024)

Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging
by: Liu, Zhilin, et al.
Published: (2026)

Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?
by: Garg, Spandan, et al.
Published: (2026)

Balancing Latency and Accuracy of Code Completion via Local-Cloud Model Cascading
by: Lu, Hanzhen, et al.
Published: (2026)

DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
by: Ma, Ming, et al.
Published: (2025)

A Generic and Efficient Python Runtime Verification System and its Large-scale Evaluation
by: Shen, Zhuohang, et al.
Published: (2025)

UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging
by: Lee, Cheryl, et al.
Published: (2024)

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis
by: Yang, Weiqing, et al.
Published: (2024)

Is LLM-Generated Code More Maintainable \& Reliable than Human-Written Code?
by: Molison, Alfred Santa, et al.
Published: (2025)

Correctness isnt Efficiency: Runtime Memory Divergence in LLM-Generated Code
by: Rajput, Prateek, et al.
Published: (2026)

The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs
by: Adnan, Muntasir, et al.
Published: (2025)

An Empirical Study of Interaction Smells in Multi-Turn Human-LLM Collaborative Code Generation
by: Zhang, Binquan, et al.
Published: (2026)

Automatic Generation of Benchmarks and Reliable LLM Judgment for Code Tasks
by: Farchi, Eitan, et al.
Published: (2024)

A Systematic Survey on Debugging Techniques for Machine Learning Systems
by: Nguyen, Thanh-Dat, et al.
Published: (2025)

A Systematic Mapping Study on the Debugging of Autonomous Driving Systems
by: Shaw, Nathan, et al.
Published: (2026)

LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
by: Rasheeda, Zeeshan, et al.
Published: (2026)

Revisit Self-Debugging with Self-Generated Tests for Code Generation
by: Chen, Xiancai, et al.
Published: (2025)

BugSpotter: Automated Generation of Code Debugging Exercises
by: Pădurean, Victor-Alexandru, et al.
Published: (2024)

CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation
by: Pan, Ruwei, et al.
Published: (2025)

RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models
by: Liu, Jingjing, et al.
Published: (2025)

MANTRA: Enhancing Automated Method-Level Refactoring with Contextual RAG and Multi-Agent LLM Collaboration
by: Xu, Yisen, et al.
Published: (2025)

Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph
by: Nainani, Jatin, et al.
Published: (2025)

Personalization of Code Readability Evaluation Based on LLM Using Collaborative Filtering
by: Hiraki, Buntaro, et al.
Published: (2024)

Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)
by: Hu, Boyue Caroline, et al.
Published: (2025)

Guided Debugging of Auto-Translated Code Using Differential Testing
by: Wu, Shengnan, et al.
Published: (2025)

AP2O-Coder: Adaptively Progressive Preference Optimization for Reducing Compilation and Runtime Errors in LLM-Generated Code
by: Zhang, Jianqing, et al.
Published: (2025)

Large Language Model Guided Self-Debugging Code Generation
by: Adnan, Muntasir, et al.
Published: (2025)

Agent That Debugs: Dynamic State-Guided Vulnerability Repair
by: Liu, Zhengyao, et al.
Published: (2025)

Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis
by: Xiang, Jiahong, et al.
Published: (2026)

CodeArena: A Collective Evaluation Platform for LLM Code Generation
by: Du, Mingzhe, et al.
Published: (2025)