# Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution

arXiv: https://arxiv.org/abs/2604.05955 · HTML: https://mlsanity.com/paper/2604.05955/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 43 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 15 of 15)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark](https://mlsanity.com/paper/2402.04788/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [Few-shot training LLMs for project-specific code-summarization](https://mlsanity.com/paper/2207.04237/) (2022)
- [Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks](https://mlsanity.com/paper/2410.20266/) (2024)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [SWE-Lancer: Can Frontier LLMs Earn 1 Million from Real-World Freelance Software Engineering?](https://mlsanity.com/paper/2502.12115/) (2025)
- [OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding](https://mlsanity.com/paper/2601.10343/) (2026)
- [Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey](https://mlsanity.com/paper/2601.11655/) (2026)
- [ISPY: Automatic Issue-Solution Pair Extraction from Community Live Chats](https://mlsanity.com/paper/2109.07055/) (2021)
- [Extracting Rationale for Open Source Software Development Decisions -- A Study of Python Email Archives](https://mlsanity.com/paper/2102.05232/) (2021)

## Built on by (most cited first, 3 of 3)

- [Is Agent Code Less Maintainable Than Human Code?](https://mlsanity.com/paper/2606.21804/) (2026)
- [SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents](https://mlsanity.com/paper/2609.04167/) (2026)
- [Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents](https://mlsanity.com/paper/2610.06193/) (2026)

## Abstract (arXiv)

Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with project-specific design constraints, such as architectural conventions, error-handling policies, and maintainability requirements, which are rarely encoded in tests and are often documented only implicitly in code review discussions. This paper introduces textitdesign-aware issue resolution and presents bench, a benchmark that makes such implicit design constraints explicit and measurable. bench is constructed by mining and validating design constraints from real-world pull requests, linking them to issue instances, and automatically checking patch compliance using an LLM-based verifier, yielding 495 issues and 1,787 validated constraints across six repositories, aligned with SWE-bench-Verified and SWE-bench-Pro. Experiments with state-of-the-art agents show that test-based correctness substantially overestimates patch quality: fewer than half of resolved issues are fully design-satisfying, design violations are widespread, and functional correctness exhibits negligible statistical association with design satisfaction. While providing issue-specific design guidance reduces violations, substantial non-compliance remains, highlighting a fundamental gap in current agent capabilities and motivating design-aware evaluation beyond functional correctness.