openreview.net · 6,187 words · saved by 1 readers
N/A
# link_w75c5x2uzs.pdf ## Metadata - PDFFormatVersion=1.5 - IsLinearized=true - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - CreationDate=D:20251229083823Z - Creator=LaTeX with hyperref - ModDate=D:20251229083823Z - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.27 (TeX Live 2025) kpathsea version 6.4.1 - Producer=pdfTeX-1.40.27 - Trapped=False ## Contents ### Page 1 ICLR 2026 Workshop on AI with Recursive Self-Improvement1 Workshop SummaryRecursive self-improvement (RSI) is moving from thought experiments to depl
saved by
related reading
- MAI-Thinking-1: Building a Hill-Climbing Machinemicrosoft.ai
- Harness Engineering for Self-Improvement | Lil'Loglilianweng.github.io
- pdfopenreview.net
- Self-Adapting Language Modelsarxiv.org
- Position: It's Time to Optimize for Self-Consistencytime-for-consistency.github.io
- [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
- NL.pdfabehrouz.github.io
- e5b5c402bb7bd5e60bede6961d6fe39e-Paper-Conference.pdfproceedings.iclr.cc
- the-illusion-of-thinking.pdfml-site.cdn-apple.com
- [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
- rsi-paper.pdfelasticity.institute
- 1b44b878bb782e6954cd888628510e90-Paper-Conference.pdfproceedings.neurips.cc