OnePred maintains a recursively updated intent memory and uses two-stage RL to predict next queries, cutting token use by up to 22x while outperforming baselines on a new NQP-Bench dataset.
ACM Transactions on Information Systems , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
IceBreaker applies resonance-aware interest distillation and interaction-oriented starter generation with preference alignment to create cold-start conversation openers, yielding +0.184% active days and +9.425% CTR gains in production A/B tests.
Conversational scenario modeling from user profiles and domain knowledge, combined with intent-keyword bridging, improves proactivity, fluency, and informativeness in target-guided proactive dialogue systems.
citing papers explorer
-
OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
OnePred maintains a recursively updated intent memory and uses two-stage RL to predict next queries, cutting token use by up to 22x while outperforming baselines on a new NQP-Bench dataset.
-
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters
IceBreaker applies resonance-aware interest distillation and interaction-oriented starter generation with preference alignment to create cold-start conversation openers, yielding +0.184% active days and +9.425% CTR gains in production A/B tests.
-
Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridging
Conversational scenario modeling from user profiles and domain knowledge, combined with intent-keyword bridging, improves proactivity, fluency, and informativeness in target-guided proactive dialogue systems.