Jiayue Pu et al. (12 authors) · 2026-10-26
Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges
“Reported gains may reflect flawed evaluations, previously acquired capabilities may deteriorate, and compliance with behavioral constraints may weaken.”
- Who
- Jiayue Pu et al. (12 authors)
- Date
- 2026-10-26
- Evidence
- Not rated. A survey that reviews other studies and reports no new measurement. how we rate evidence
- Replication
- Nothing to rerun. all claims
- Checked
- 2026-10-28, against the source page
- Links
- Source Paper
Also on the page
- A survey. Its abstract defines RSI this way: "Recursive self-improvement (RSI) extends this process to inductive biases and to the mechanisms that govern future updates, which can themselves be revised and reused across improvement cycles."
- It reviews risks and evaluation evidence "while distinguishing direct RSI findings from evidence in related systems".