Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale

Researchers submitted ARCTIC, an AI-powered Code Critique system, to arXiv on 31 Jul 2026 (revised 14 Aug 2026), reporting that its intent prediction achieves 0.86 F1, drift detection reaches QWK = 0.907 against human annotators, and code spotlight outperforms the baseline AI reviewer by 2.4x on quality estimation at 5x fewer tokens. In an experimental rollout, ARCTIC's drift scores reduced code misalignment by an additional 5.76 points (p = 0.026), intent prediction received 90.2% approval, and zero defects have been attributed to self-reviewed diffs since launch. The system targets correctness, security, and performance concerns that existing AI code review tools under-index, grounding its three capabilities in a six-theme taxonomy derived from 18,000 code reviews.

Computer Science Software Engineering Submitted on 31 Jul 2026 v1 https://arxiv.org/abs/2607.29516v1 , last revised 14 Aug 2026 this version, v2 Title:From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale View PDF https://arxiv.org/pdf/2607.29516 HTML experimental https://arxiv.org/html/2607.29516v2 Abstract:AI coding agents are generating code at volumes that exceed the capacity of traditional peer review. At the same time, existing AI code review tools over-index on low-value suggestions such as style and best practices while under-indexing on the concerns human reviewers prioritize most: correctness, security, and performance. We present ARCTIC, an AI-powered Code Critique system that reframes code review around three capabilities: intent prediction, which infers why a change was made from conversation logs and metadata; drift detection, which measures divergence between the developer's intent and the agent's output via backtranslation; and code spotlight, which ranks the regions of a diff most warranting human scrutiny. We ground these capabilities in a six-theme taxonomy derived from 18,000 code reviews. Offline evaluation shows that intent prediction achieves 0.86 F1, drift detection reaches near-perfect ordinal agreement with human annotators QWK = 0.907 , and spotlight outperforms the baseline AI reviewer by 2.4x on quality estimation at 5x fewer tokens. In the experimental rollout, the drift scores reduces code misalignment by an additional 5.76 points p = 0.026 , intent prediction receives 90.2% approval, and zero defects have been attributed to self-reviewed diffs since launch. Submission history From: Chandra Maddila view email https://arxiv.org/show-email/aa027733/2607.29516 Fri, 31 Jul 2026 15:17:25 UTC 1,613 KB \ v1\ https://arxiv.org/abs/2607.29516v1 v2 Fri, 14 Aug 2026 15:44:33 UTC 1,613 KB 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 .