RECAP trains a streaming LLM profile updater with GRPO rewards from a dual-tower evaluator, gaining +0.0084 uAUC (cleaned eval) and +0.139% online usage time.
Title resolution pending
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · OpenAlex
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation
RECAP trains a streaming LLM profile updater with GRPO rewards from a dual-tower evaluator, gaining +0.0084 uAUC (cleaned eval) and +0.139% online usage time.