Recursive Synthetic Terminal Tasks generates 37,000+ verifiable long-horizon agent tasks

Research official 1 src. ~1 min

Introduces Recursive Synthetic Terminal Tasks (RST), a recursive verified-synthesis framework that automatically generates over 37,000 verifiable long-horizon terminal-agent tasks, keeping instructions, environments, solutions, and verifiers consistent at roughly $0.05 per task. Task difficulty compounds across rounds, with median reference-solution length growing from 67 to 374 lines and DeepSeek-V4-Pro pass@4 dropping from 90% to 2.5% over 15 rounds.

Why it matters

Reported with high upvotes on HuggingFace Daily Papers; offers a scalable, cheap way to generate hard agentic training/eval data as terminal-agent benchmarks saturate.

Importance: 3/5

HF Daily Papers with high upvotes bump applied.

Sources