Skip to main content
Search

Xuanren Chen

1 related articles

Subscribe to updates
  1. arXiv

    Long-horizon agent training stops comparing inside one task: BLPO pools experience across tasks, lifting WebShop success to 74.02%

    In long-horizon tasks, the contribution of each agent step is hard to separate from a single trajectory, and restricting comparisons to the few rollouts of one task often leaves too little evidence. BLPO groups decisions that reach the same task progress and perform the same action function across tasks, estimates step-level advantages from statistics accumulated across tasks and training updates, and weights them for context difficulty and reliability. On ALFWorld and WebShop, the Qwen2.5-1.5B policy raises WebShop task success from HGPO's 71.54% to 74.02% and ALFWorld Out-Success from 90.16% to 91.54%, without a learned critic or extra rollouts.

You’re all caught up