RST: Recursive Synthesis for Long-Horizon Terminal Tasks
Zhongzhi Li, Yucheng Shi‡, Zongxia Li*, Ruhan Wang, Anhao Li, Zixun Huang, Junyao Yang, Lei Ke, Ninghao Liu, Haitao Mi, Leowei Liang
- Equal contribution · ‡ Project lead (marked † in the source paper)
Recursive verified synthesis expands long-horizon terminal tasks by extending successful solutions and realigning instructions and verifiers. It yields 37,484 tasks at approximately $0.05 each and improves Qwen3.5 by up to 10 points across terminal benchmarks.