AI peer review iteration fails to converge due to never-satisfied reviewer
ChenhaoTan · x · 2026-08-21
Inspired by a discussion, the author tested whether AI revising a paper based on AI reviews would reach a fixed point. The initial experiment suggests the answer is No in the current setup, as the system encounters a never-satisfied reviewer. Links to the manuscript, repo, and idea are provided.
Related event: Experiment shows AI paper revision loops never converge(2 posts)→
More from Research
- ImageNet should retire: DiT method rankings negatively correlate between ImageNet and text-to-image — YouJiacheng · 2026-10-16
- GAE paper learns a geometry-native latent space for 3D-consistent world generation — yshan2u · 2026-10-16
- Agents turn conservative as context grows: edits shrink from 150 to 30 lines — dbreunig · 2026-10-16
- LMR-BENCH at EMNLP 2025 tests whether LLM agents can reproduce real LLM research — ZhiyuChen4 · 2026-10-16
- Ex-OpenAI researcher claims most neurons are legible now; critics call it hype — anshulkundaje · 2026-10-16
- Physicist pushes back on ML community's acceptance that models may be beyond understanding — tszzl · 2026-10-16