Paper recorded by Signals 4 on 2026-09-17 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18
Category: cs.AI · 人工智能 · first seen 2026-09-18
Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment observations as context but not as prediction targets. We ask whether this convention provides the best initialization for subsequent reinforcement learning. We introduce ActObs, which also supervises the observation toke