Specialist agents in an autonomous research loop with lineage feedback improve ML training recipes, delivering 0.81% better validation bpb on Parameter Golf, 38.7% higher CORE on NanoChat-D12, and 4.59% lower wallclock on CIFAR-10 Airbench96 across 1797 trials with no human intervention after setup.
Esteban Real, Chen Liang, David R
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
Specialist agents in an autonomous research loop with lineage feedback improve ML training recipes, delivering 0.81% better validation bpb on Parameter Golf, 38.7% higher CORE on NanoChat-D12, and 4.59% lower wallclock on CIFAR-10 Airbench96 across 1797 trials with no human intervention after setup.