SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents
Training long-horizon agents to solve complex tasks requires effective supervision over extended interaction sequences. However, sparse terminal rewards obscure intermediate contributions, while on-policy distillation can lose informative teacher guidance as student-generated histories grow. To address this problem, we...
Shang-Yang Wu, Shuai Zhao, Zi-Yue Zhu et al.
· 0 citations