5 papers
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
Langzhou He, Junyou Zhu, Yue Zhou +7
Agentic reinforcement learning trains large language models using multi-turn trajectories that interleave long reasoning traces with short environment-facing actions. Common policy…
RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems
Junhua Liu, Yang Jihao, Cheng Chang +3
Proactive intent prediction is a critical capability in modern e-commerce chatbots, enabling "zero-query" recommendations by anticipating user needs from behavioral and contextual…
From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification
Junhua Liu, Yong Keat Tan, Bin Fu +1
In conversational AI systems, a critical challenge in training effective multi-turn intent classification models lies in the generation of large-scale, domain-specific, multilingua…
Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production
Junhua Liu, Yong Keat Tan, Bin Fu +1
Accurate multi-turn intent classification is essential for advancing conversational AI systems. However, challenges such as the scarcity of comprehensive datasets and the complexit…
Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact
Junhua Liu, Bin Fu
Multilingual Large Language Models (MLLMs) represent a pivotal advancement in democratizing artificial intelligence across linguistic boundaries. While theoretical foundations are…