Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents cover art

Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents

Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents

Listen for free

View show details
Terminal-using agents trained with reinforcement learning handle multi-step coding and debugging, but standard credit assignment ignores that later commands depend on earlier outputs, so training signals can land on irrelevant steps. DepGPO builds a command dependency graph from execution traces, traces backward from resources the task verifier inspects, and assigns credit to relevant writes and their supporting reads, redistributing trajectory advantages across steps. Experiments show better task performance and training stability on complex terminal tasks. Authors: Yu Li, Guangfeng Cai, Long-Fei Li, Shuo Han, Shengtian Yang, Han Luo, Kaibing Yang, Lei Feng Paper: https://arxiv.org/abs/2610.03634v1
adbl_web_anon_alc_button_suppression_t1
No reviews yet