Hierarchical process-level generative reward modeling with adaptive long-horizon reasoning for robust LLM alignment.

@article{chen-2026-hierarchical, author = {Shikun Chen and Yangguang Liu}, title = {{Hierarchical process-level generative reward modeling with adaptive long-horizon reasoning for robust LLM alignment}}, journal = {Information Processing and Management}, volume = {63}, number = {8}, pages = {104957}, year = {2026}, url = {https://doi.org/10.1016/J.IPM.2026.104957}, doi = {https://doi.org/10.1016/J.IPM.2026.104957} }