original paper

Recursive Self-Improvement through Multi-Agent Self-Supervision

MASS authors (UC Berkeley and Sakana AI) · Published 2026-10-08

Read the original document ↗

Evidence from this source

Results and research linked to this document
Type	Evidence
Paper / report	Recursive Self-Improvement through Multi-Agent Self-Supervision Source details Primary publication source

Document tracking details

Source ID: src-mass-v1
Source type: Primary
Original URL: https://arxiv.org/html/2610.12176v1
Retrieved URL: https://arxiv.org/html/2610.12176v1
Last updated by publisher: Not reported
Access status: available
Retrieved: 2026-10-11T20:14:47.419Z
Document fingerprint: 09549b341ddbb99961e763e2536fc9f28eb2fb12d5319ae9f327abb4d557cde1
Based on original bytes. Used to detect changes to the source.

Availability checks

2026-10-11T20:14:47.419Z · success: Original HTML retained; selected claim-relevant methods/results inspected. Source extraction only; no experiments executed.