Cover Image

CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lyu, Zongyi, Ji, Zhenlan, Chen, Songqiang, Wang, Liwen, Huang, Yuheng, Wang, Shuai, Cheung, Shing-Chi
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

Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation
by: Lyu, Zongyi, et al.
Published: (2025)

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

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

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

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

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

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

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

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

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

Evaluating LLMs on Sequential API Call Through Automated Test Generation
by: Huang, Yuheng, et al.
Published: (2025)

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

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

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

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

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

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

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

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

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

Optimization-Aware Test Generation for Deep Learning Compilers
by: Shen, Qingchao, et al.
Published: (2025)

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

Metamorphic Testing of Image Captioning Systems via Image-Level Reduction
by: Xie, Xiaoyuan, et al.
Published: (2023)

Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation
by: Zhu, Qiming, et al.
Published: (2025)

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

GeoJSON Agents:A Multi-Agent LLM Architecture for Geospatial Analysis-Function Calling vs Code Generation
by: Luo, Qianqian, et al.
Published: (2025)

SolAgent: A Specialized Multi-Agent Framework for Solidity Code Generation
by: Chen, Wei, et al.
Published: (2026)

How Far are App Secrets from Being Stolen? A Case Study on Android
by: Wei, Lili, et al.
Published: (2025)

MT4DP: Data Poisoning Attack Detection for DL-based Code Search Models via Metamorphic Testing
by: Chen, Gong, et al.
Published: (2025)

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

Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents
by: Liu, Zihan, et al.
Published: (2024)

FastLog: An End-to-End Method to Efficiently Generate and Insert Logging Statements
by: Xie, Xiaoyuan, et al.
Published: (2023)

LLM-based Multi-Agent System for Intelligent Refactoring of Haskell Code
by: Siddeeq, Shahbaz, et al.
Published: (2025)

Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation
by: Xiong, Qian, et al.
Published: (2025)

From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
by: Wang, Yawen, et al.
Published: (2026)

Can Large Language Models Model Programs Formally?
by: Chen, Zhiyong, et al.
Published: (2026)

MR-Scout: Automated Synthesis of Metamorphic Relations from Existing Test Cases
by: Xu, Congying, et al.
Published: (2023)

Towards Understanding the Characteristics of Code Generation Errors Made by Large Language Models
by: Wang, Zhijie, et al.
Published: (2024)

COCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledge
by: Li, Yichen, et al.
Published: (2025)

A Tale of Two DL Cities: When Library Tests Meet Compiler
by: Shen, Qingchao, et al.
Published: (2024)