Paper recorded by Signals 4 on 2026-09-30 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-30 on arXiv · recorded by Signals 4 on 2026-10-01
Category: cs.AI · 人工智能 · first seen 2026-10-01
On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories. However, in multi-turn interaction, an incorrect action changes the states the student encounters later, so errors compound across turns. In preliminary experiments across three Qwen3 models (8B to 235B), we find that more than half of the failed