Constraint Decay: The Fragility of LLM Agents in Back End Code Generation

A new study published on arXiv reveals that large language model agents suffer from "constraint decay," losing an average of 30 points in assertion pass rates when generating backend code with strict structural requirements. Researchers found that agents perform well under loose specifications but fail dramatically as architectural constraints accumulate, with weaker configurations approaching zero success rates. The study identifies data-layer defects, particularly incorrect query composition and ORM runtime violations, as the primary cause of failure, highlighting a critical gap in current coding agent capabilities for production-grade software development.

Computer Science Software Engineering Submitted on 7 May 2026 Title:Constraint Decay: The Fragility of LLM Agents in Backend Code Generation View PDF /pdf/2605.06445 HTML experimental https://arxiv.org/html/2605.06445v1 Abstract:Large Language Model LLM agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requires strict adherence to structural constraints, such as architectural patterns, databases, and object-relational mappings. Existing benchmarks often overlook these non-functional requirements, rewarding functionally correct but structurally arbitrary solutions. We present a systematic study evaluating how well agents handle structural constraints in multi-file backend generation. By fixing a unified API contract across 80 greenfield generation tasks and 20 feature-implementation tasks spanning eight web frameworks, we isolate the effect of structural complexity using a dual evaluation with end-to-end behavioral tests and static verifiers. Our findings reveal a phenomenon of constraint decay: as structural requirements accumulate, agent performance exhibits a substantial decline. Capable configurations lose 30 points on average in assertion pass rates from baseline to fully specified tasks, while some weaker configurations approach zero. Framework sensitivity analysis exposes significant performance disparities: agents succeed in minimal, explicit frameworks e.g., Flask but perform substantially worse on average in convention-heavy environments e.g., FastAPI, Django . Finally, error analysis identifies data-layer defects e.g., incorrect query composition and ORM runtime violations as the leading root causes. This work highlights that jointly satisfying functional and structural requirements remains a key open challenge for coding agents. References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .