Tag
Google Research publicly released Deep Review, an agentic AI system for rigorous technical document review across academic, legal, and finance domains, evolving from its Paper Assistant Tool pilots with major CS conferences. It offers tiered access with a scalable Gemini API and guarantees uploaded documents are not used for model training.
The paper introduces Rhetorical Robustness as an evaluation target for AI scientific reviewers, proposes the RobustReview benchmark with 1,260 manuscript versions, and presents SciCore, a dual-branch reviewer that combines full-manuscript assessment with a science-core-extracted judgment to improve stability while maintaining human alignment.
An individual discusses building a tool for independent AI review in agentic workflows, which is being used as a gate in various AI-driven processes for merge/release reviews.
A Twitter user shared a prompt that uses Terence Tao's 'dumb questions' method to stress-test any plan by asking critical questions to uncover hidden assumptions and improve understanding.
Harness launched a new code repository with AI-powered code review designed for teams using AI coding agents, featuring scoped permissions and risk-based diff grouping to integrate review policies directly into the agent workflow.
The article explains that AI review loops in code development can become unstable due to inconsistent AI opinions, scope creep, and hallucinations, as shown in a test with Opus 5.
A hands-on review of Qwen 3.8 Max, highlighting its speed, strong planning and simplification skills, experimental rigor, and creative implementation abilities.
This paper investigates how rhetorical framing biases AI-based peer review scores, finding that evidence framing and novelty stance have the largest effects and that score movements depend on the reviewer's initial score and evaluation strictness.
An experience report from BOSC 2026 on using generative AI to pre-review open-source software submissions, with human reviewers making final decisions. Most reviewers found the AI-assisted pre-review useful but preferred to verify AI conclusions independently.
Elon Musk tweets a link to a positive review of Grok 4.5.
Chintan Turakhia, engineering lead at Coinbase, shares how the team used AI for code review, reducing PR review time from 150 hours to 15 hours, and setting a record of merging 70 PRs in 15 minutes. He emphasizes focusing on solving problems rather than just talking about adopting AI.
The author built an AI-powered PR review workflow that generates actual fix PRs instead of just comments, claiming to be 6x cheaper than CodeRabbit and more accurate on large PRs.