HRPO decomposes item-level rewards into token-level 'residual credits' along semantic identifier hierarchies and optimizes the generator with a PPO-style objective, improving session utility in KuaiSim and production A/B tests.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Hierarchical Residual Policy Optimization for Generative Recommendations
HRPO decomposes item-level rewards into token-level 'residual credits' along semantic identifier hierarchies and optimizes the generator with a PPO-style objective, improving session utility in KuaiSim and production A/B tests.