original paper · primary source

AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement

Publisher: AI4AI-Bench authors · publication date: 2026-08-20 (day)

Original document

Exact source locators
Record type	Record	Locator
Evidence	a4-opus-mean	§3.2, Figure 2 prose
Evidence	a4-sol-mean	§3.2, Figure 2 prose
Evidence	a4-kimi-mean	§3.2, Figure 2 prose
Evidence	a4-sonnet-mean	§3.2, Figure 2 prose
Evidence	a4-terra-mean	§3.2, Figure 2 prose
Evidence	a4-luna-mean	§3.2, Figure 2 prose
Benchmark	AI4AI-Bench	§§2–3; Figure 2 and Table 2
Paper / report	AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement	Primary publication source

2026-09-26T04:47:27Z · success: Original source inspected by Codex; extraction check, not experimental replication.