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
Podden och tillhörande omslagsbild på den här sidan tillhör
Craig Spencer Smith. Innehållet i podden är skapat av Craig Spencer Smith och inte av,
eller tillsammans med, Poddtoppen.
