Evidence item

AIDE² autonomously produced seven successive improvements to an AI research agent over eight days, with gains transferring to held-out tasks. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 10368

Source: Recursive self-improvement of AI research agents · locator {} · excerpt hash sha256:488a5334177f43e4531f06b757a5ef3723d795112217bf44641e2d0cc7cac272

Exact excerpt

In an autonomous 8-day run, AIDE² discovered seven successive improvements, ranging from a new search policy to memory mechanisms that compress and manage the agent’s growing context. ... Together, these results show that an AI research agent can improve its own research efficiency through recursive self-improvement, and that these gains transfer to tasks and domains the loop never encountered.

Linked claims

Claim	Direction	Relevance	Steps	Counted
c80f973e	SUPPORT	DIRECT	1	yes

Audits

None.