Deep Review launches publicly: 16k papers reviewed, math errors found in over a third
yshan2u · x · 2026-10-16
Deep Review, an AI paper-assistant tool for CS/ML conferences, is now publicly available. Born from a STOC partnership a year ago, it has reviewed 16k+ submissions with ICML, NeurIPS, ICLR and AISTATS, found significant math errors in over 1/3 of papers that used it, and prompted 58% of ICLR authors to run entirely new experiments. The public launch brings improvements and expanded access for all authors.
More from coding & agent
- Four Gemini 4 Argon agents beat Minecraft's Ender Dragon autonomously in 27 hours — Maxence Faldor · 2026-10-16
- Tencent's Terminal-RSI builds recursively self-improving terminal agents, hitting 19.84% on Terminal-Bench 4.0 — tencent · 2026-10-16
- Tsinghua's AutoSFT uses multi-agent collaboration to automate SFT data research — TsinghuaNLP · 2026-10-16
- ByteDance's Athanor: autonomous agents post-train a small model to match its official tuned version — Yufa Zhou · 2026-10-16
- NVIDIA's EdgeWise cuts long-horizon agent inference costs up to 62% via selective cloud delegation — nvidia · 2026-10-16
- Intern-Decision: 0.8B-4B multimodal decision models output structured choices in one forward pass — internlm · 2026-10-16