Cover Image

AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vangala, Bhanu Prakash, Adibifar, Ali, Gehani, Ashish, Malik, Tanu
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Artificial Intelligence Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software Development
by: Bowers, Brian, et al.
Published: (2025)

The Specification Gap: Coordination Failure Under Partial Knowledge in Code Agents
by: Sartori, Camilo Chacón
Published: (2026)

CodeCureAgent: Automatic Classification and Repair of Static Analysis Warnings
by: Joos, Pascal, et al.
Published: (2025)

LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems
by: Prakash, Sunil
Published: (2026)

AutoFSM: A Multi-agent Framework for FSM Code Generation with IR and SystemC-Based Testing
by: Luo, Qiuming, et al.
Published: (2025)

SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies
by: Saxena, Siddhant, et al.
Published: (2026)

From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work
by: Rosen, Josh, et al.
Published: (2026)

Bridging the Prototype-Production Gap: A Multi-Agent System for Notebooks Transformation
by: Elhashemy, Hanya, et al.
Published: (2025)

Resolving Java Code Repository Issues with iSWE Agent
by: Ganhotra, Jatin, et al.
Published: (2026)

ResearchCodeAgent: An LLM Multi-Agent System for Automated Codification of Research Methodologies
by: Gandhi, Shubham, et al.
Published: (2025)

Code2MCP: Transforming Code Repositories into MCP Services
by: Ouyang, Chaoqian, et al.
Published: (2025)

ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents
by: Di, Shimin, et al.
Published: (2026)

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
by: Zhou, Chenyu, et al.
Published: (2026)

No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows
by: Raghavan, Siddeshwar, et al.
Published: (2026)

Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports
by: Gon, Mahmut Furkan, et al.
Published: (2026)

Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Modernization
by: Lwin, Naing Oo, et al.
Published: (2026)

Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization
by: Ishibashi, Yoichi, et al.
Published: (2024)

ABMax: A JAX-based Agent-based Modeling Framework
by: Chaturvedi, Siddharth, et al.
Published: (2025)

Real-Time BDI Agents: a model and its implementation
by: Traldi, Andrea, et al.
Published: (2022)

Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary
by: Hoda, Rashina
Published: (2025)

The Hidden Bloat in Machine Learning Systems
by: Zhang, Huaifeng, et al.
Published: (2025)

Cognitive Agents Powered by Large Language Models for Agile Software Project Management
by: Cinkusz, Konrad, et al.
Published: (2025)

REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement
by: Pabba, Anvith, et al.
Published: (2025)

Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review
by: Yang-Smith, Corey, et al.
Published: (2026)

Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls
by: Zhang, Zeyu, et al.
Published: (2026)

Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development
by: Koch, Christopher
Published: (2026)

Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
by: Liu, Yuanzhe, et al.
Published: (2025)

Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents
by: Bhardwaj, Varun Pratap
Published: (2026)

Multi-Agent LLM Committees for Autonomous Software Beta Testing
by: Karanam, Sumanth Bharadwaj Hachalli, et al.
Published: (2025)

RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection
by: Abuzakuk, Sami, et al.
Published: (2026)

Facilitating Trustworthy Human-Agent Collaboration in LLM-based Multi-Agent System oriented Software Engineering
by: Ronanki, Krishna
Published: (2025)

AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems
by: Li, Yang, et al.
Published: (2025)

$λ_A$: A Typed Lambda Calculus for LLM Agent Composition
by: Liu, Qin
Published: (2026)

CodeAD: Synthesize Code of Rules for Log-based Anomaly Detection with LLMs
by: Huang, Junjie, et al.
Published: (2025)

A Generic Modelling Framework for Last-Mile Delivery Systems
by: Gürcan, Önder, et al.
Published: (2025)

IACT: A Self-Organizing Recursive Model for General AI Agents: A Technical White Paper on the Architecture Behind kragent.ai
by: Lu, Pengju
Published: (2025)

The Lifecycle Workbench -- A Configurable Framework for Digitized Product Maintenance Services
by: Briechle, Dominique, et al.
Published: (2025)

Qualixar OS: A Universal Operating System for AI Agent Orchestration
by: Bhardwaj, Varun Pratap
Published: (2026)

Assessing and Enhancing the Robustness of LLM-based Multi-Agent Systems Through Chaos Engineering
by: Owotogbe, Joshua
Published: (2025)

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
by: Feng, Yukang, et al.
Published: (2026)