4 papers
SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment
Hongxiang Lin, Zhirui Kuai, Erpeng Xue +1
Structured skill prompts improve exploration in long-horizon agentic reinforcement learning (RL). Skill-augmented RL methods retain external skills at inference, while skill-intern…
Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting
Hongxiang Lin, Zhirui Kuai, Erpeng Xue +1
Test-time reinforcement learning (TTRL) reports substantial accuracy gains on mathematical reasoning benchmarks using majority vote as a pseudo-label signal. We argue these gains a…
MTmixAtt: Integrating Mixture-of-Experts with Multi-Mix Attention for Large-Scale Recommendation
Xianyang Qi, Yuan Tian, Zhaoyu Hu +4
Industrial recommender systems critically depend on high-quality ranking models. However, traditional pipelines still rely on manual feature engineering and scenario-specific archi…
Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval
Zhirui Kuai, Zuxu Chen, Huimu Wang +11
Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and…