The authors encoded the research workflow as an Executable Operating Protocol, a state machine specifying phases, decision gates, branches and loops.
Cross-checking coding agents improves reliability in automated model research
RankEvolve combines a runtime-enforced workflow with mutually reviewing coding agents, improving execution accuracy under matched compute budgets.
Industry
Zheng Chen · Linfeng Liu · Hong Li · Hong Yan
Meta
Research Digest··3 min read
Chen and colleagues present RankEvolve, a harness that automates repeated proposal, implementation, training and evaluation of ranking-model changes while enforcing a predefined experimental process.
Why this paper
From Meta
In one line
Runtime-enforced composition of coding agents raises all-oracle execution accuracy to 62.5% from a 45.8% single-product baseline in auto-research for ranking models.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§