aiqbench analysis
This research identifies significant misalignments between Pull Requests and their linked issues in standard software engineering benchmarks like SWE-bench, which can skew evaluations of Large Language Models' problem-solving capabilities. The authors introduce PAIChecker, a multi-agent system that effectively detects these inconsistencies to ensure more reliable benchmark construction for future AI development cycles.
PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks
arXiv:2607.28587v2 Announce Type: replace-cross Abstract: SWE-bench-like benchmarks are widely used for evaluating LLM's issue resolution capability. They typically follow a common construction pipeline: each PR (Pull Request) is paired with its linked issue by extracting issue references from the PR description; the issue description is used as the problem statement, and the PR patch serves as the test oracle. However, due to the inherent complexity of developing and maintaining large repositories, such PR-Issue pairings are often misaligned in practice. In this work, we systematically study SWE-bench Verified instances, finding that 13.6% exhibit misalignment across five patterns in eleven fine-grained scenarios. To enable reliable and scalable construction of those benchmarks in the future, we propose PAIChecker, a multi-agent system for checking PR-Issue misalignment in SWE-bench-like benchmarks. Specifically, PAIChecker adopts a three-phase design that combines specific pattern identification, cross-agent label synthesis, and code-level validation, thereby enabling more accurate, generalizable, and progressively verified detection. Experiments on SWE-Gym and SWE-bench Multilingual show that PAIchecker achieves the best performance across all four LLM backbones, reaching up to 92.12% and 91.67% binary accuracy, respectively.
Abstract:SWE-bench-like benchmarks are widely used for evaluating LLM's issue resolution capability. They typically follow a common construction pipeline: each PR (Pull Request) is paired with its linked issue by extracting issue references from the PR description; the issue description is used as the problem statement, and the PR patch serves as the test oracle. However, due to the inherent complexity of developing and maintaining large repositories, such PR-Issue pairings are often misaligned in practice. In this work, we systematically study SWE-bench Verified instances, finding that 13.6% exhibit misalignment across five patterns in eleven fine-grained scenarios. To enable reliable and scalable construction of those benchmarks in the future, we propose PAIChecker, a multi-agent system for checking PR-Issue misalignment in SWE-bench-like benchmarks. Specifically, PAIChecker adopts a three-phase design that combines specific pattern identification, cross-agent label synthesis, and code-level validation, thereby enabling more accurate, generalizable, and progressively verified detection. Experiments on SWE-Gym and SWE-bench Multilingual show that PAIchecker achieves the best performance across all four LLM backbones, reaching up to 92.12% and 91.67% binary accuracy, respectively.
Accepted at the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026). Github Repo: this https URL
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
arXiv:2607.28587 [cs.SE]
(or arXiv:2607.28587v2 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2607.28587 Focus to learn more arXiv-issued DOI via DataCite
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.
Full text under the publisher's open licence · 286 words
Related coverage

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026

Why do models task game?
AI Alignment Forum · Aug 6, 2026

Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · Aug 3, 2026

Academia is for Ambition — Alex Zhang, MIT
Latent Space · Oct 2, 2026