pith. sign in

You must observe at least one tool feedback (execution result wrapped in<tool_response>...</tool_response> tags) before deciding to end

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Synthetic Sandbox for Training Machine Learning Engineering Agents

cs.CL · 2026-04-06 · unverdicted · novelty 7.0

SandMLE generates micro-scale synthetic MLE environments from seed tasks to enable 13x faster on-policy RL training, delivering 20-67% gains over SFT on MLE-bench-lite and better generalization to new scaffolds.

citing papers explorer

Showing 1 of 1 citing paper.

  • Synthetic Sandbox for Training Machine Learning Engineering Agents cs.CL · 2026-04-06 · unverdicted · none · ref 4

    SandMLE generates micro-scale synthetic MLE environments from seed tasks to enable 13x faster on-policy RL training, delivering 20-67% gains over SFT on MLE-bench-lite and better generalization to new scaffolds.