Living review: LLM-panel screening hits 1.00 sensitivity, reruns monthly
maier_ak · x · 2026-10-30
The Active Matter Living Review automates the PRISMA-2020 workflow and reruns it monthly to fight review staleness. Screening uses three open-weight LLMs voting per record (two votes to include); on a 200-record human-labeled sample with a ≥0.95 sensitivity target, the panel achieved 1.00 sensitivity and 0.98 specificity — a complete working pipeline for LLM-automated systematic review.
Related event: Living review uses LLMs to auto-update systematic reviews monthly(4 posts)→
More from coding & agent
- kalomaze: agents keep sneaking MSE regression losses into multimodally conditional ML problems — kalomaze · 2026-10-30
- DeepseekHarness-Android runs DeepSeek agent on any phone with one rootless APK — vista8 · 2026-10-30
- OpenAI opens Codex Ambassadors applications: free ChatGPT Pro, API credits, DevDay invites — paw_lean · 2026-10-30
- agy-swap: Open-source Go TUI to Switch Google Antigravity Accounts and Track Model Quota — aklkbqx · 2026-10-30
- Reverse engineering any website with one Claude prompt: Claude Code clones award-winning sites via GitHub and Vercel — rubenhassid · 2026-10-30
- Thenwise Adds Cross-Session Memory to Claude Code: 83% vs 47% Accuracy, 40% Fewer Tokens — dheeraj_ponnaganti · 2026-10-30