# DAIR.AI highlights Meta’s RankEvolve, which pairs Claude Code and Codex

DAIR.AI describes RankEvolve, from a Meta paper, as a protocol that runs Claude Code and Codex as separate nodes to review and repair each other’s changes. At a matched budget, execution accuracy rises from 45.8% to 62.5%, and twelve iterations improve HSTU’s NDCG@10 on MovieLens-20M by 4.48%.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-10-24T10:07:00.000Z
Query date (America/Los_Angeles): 2026-10-24

HTML: https://didcodexreset.com/news/d75305515279426bb2b27efe.html

Content language: en
Localization state: sameLanguage

Source: DAIR.AI · Published 10/3/2026, 16:50:31

DAIR.AI describes RankEvolve, from a Meta paper on reliable auto-research agents, as a system that enforces each research phase and gate through a compiled protocol. It runs Claude Code and Codex as separate nodes that review and repair each other’s changes, aimed at silent experiment bugs such as leaked evaluation data or a disconnected gradient.

At a matched budget, combining the two products raises execution accuracy from 45.8% for the best single product to 62.5%. Over twelve iterations on the open-source HSTU recommender, RankEvolve improved NDCG@10 on MovieLens-20M by 4.48% over the published result. The write-up links to the [RankEvolve paper on DAIR.AI Academy](https://academy.dair.ai/papers/rankevolve-a-reliable-multi-agent-auto-research-harness-for-evolving-ranking-mod-2609.39551).

Tags: RankEvolve, Meta, Claude Code, Codex, Auto-research

[View original post](https://x.com/dair_ai/status/2106529236676976773)