Recursive Synthesis for Long-Horizon Terminal Tasks

Published
Source
arXiv
Paper number
835
Field
AI / General
arXiv ID
2608.05466

Key points

  • Recursive synthesis makes tasks progressively harder while preserving consistency across instructions, environments, answers, and verifiers.
  • After 15 rounds, it generates 37,484 tasks, and the synthesis yield does not fall, which means there is no apparent ceiling.
  • The intermediate answer length grows from 67 lines to 374 lines, which is a 5.6 times increase, and the number of instructions increases by more than 6 times.
  • When the synthetic data is used for SFT and PPO training, performance improves by up to 10 points on Terminal-Bench 2, Hard, and Long-Horizon tasks.
  • DeepSeek-V4-Pro pass@4 falls from 90 percent to 2.5 percent, which shows that the tasks become substantially harder.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)