Cover Image

Constraint Decay: The Fragility of LLM Agents in Backend Code Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dente, Francesco, Satriani, Dario, Papotti, Paolo
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

Text2Stories: Evaluating the Alignment Between Stakeholder Interviews and Generated User Stories
by: Dente, Francesco, et al.
Published: (2025)

CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
by: Lam, Man Ho, et al.
Published: (2025)

Towards Automated Formal Verification of Backend Systems with LLMs
by: Xu, Kangping, et al.
Published: (2025)

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development
by: Yang, Jie, et al.
Published: (2026)

AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
by: Zhu, Yuecai, et al.
Published: (2026)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
by: Guo, Chengquan, et al.
Published: (2024)

Investigating The Smells of LLM Generated Code
by: Paul, Debalina Ghosh, et al.
Published: (2025)

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

Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation
by: Liu, Mingwei, et al.
Published: (2025)

Uncertainty Quantification for LLM-based Code Generation
by: Xu, Senrong, et al.
Published: (2026)

AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device Optimization
by: Fan, Guangxi, et al.
Published: (2025)

Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation
by: Vartziotis, Tina, et al.
Published: (2024)

A Performance Study of LLM-Generated Code on Leetcode
by: Coignion, Tristan, et al.
Published: (2024)

Bias Testing and Mitigation in LLM-based Code Generation
by: Huang, Dong, et al.
Published: (2023)

Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting
by: Ye, Tong, et al.
Published: (2024)

SEMAG: Self-Evolutionary Multi-Agent Code Generation
by: Peng, Yulin, et al.
Published: (2026)

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
by: He, Yicheng, et al.
Published: (2026)

AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers
by: Lin, Zijie, et al.
Published: (2025)

AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
by: Nunez, Ana, et al.
Published: (2024)

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
by: Liu, Fang, et al.
Published: (2024)

Hallucination in LLM-Based Code Generation: An Automotive Case Study
by: Pavel, Marc, et al.
Published: (2025)

Resilient Write: A Six-Layer Durable Write Surface for LLM Coding Agents
by: Agyemang, Justice Owusu, et al.
Published: (2026)

Identifying Performance-Sensitive Configurations in Software Systems through Code Analysis with LLM Agents
by: Wang, Zehao, et al.
Published: (2024)

Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach
by: Ashiga, Mari, et al.
Published: (2025)

ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation
by: Zhao, Yicong, et al.
Published: (2025)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
by: Chen, Zhi, et al.
Published: (2026)

SpecMap: Hierarchical LLM Agent for Datasheet-to-Code Traceability Link Recovery in Systems Engineering
by: Nipane, Vedant, et al.
Published: (2026)

ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents
by: He, Jiawei, et al.
Published: (2026)

TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment
by: Yuan, Zhiqiang, et al.
Published: (2024)

ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas
by: Peng, Wenjun, et al.
Published: (2026)

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

Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
by: Akli, Amal, et al.
Published: (2026)

The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
by: Ye, Hengzhi, et al.
Published: (2026)

Verifying LLM-Generated Code in the Context of Software Verification with Ada/SPARK
by: Cramer, Marcos, et al.
Published: (2025)

Using a Feedback Loop for LLM-based Infrastructure as Code Generation
by: Palavalli, Mayur Amarnath, et al.
Published: (2024)

Uncovering Intention through LLM-Driven Code Snippet Description Generation
by: Nugroho, Yusuf Sulistyo, et al.
Published: (2025)

Toward Automated and Trustworthy Scientific Analysis and Visualization with LLM-Generated Code
by: Chakroborti, Apu Kumar, et al.
Published: (2025)

Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering
by: Ravuri, Chaitanya, et al.
Published: (2025)

Risks of ignoring uncertainty propagation in AI-augmented security pipelines
by: Mezzi, Emanuele, et al.
Published: (2024)

TDD Governance for Multi-Agent Code Generation via Prompt Engineering
by: Hasanli, Tarlan, et al.
Published: (2026)