9 papers
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
Hybrid post-training combining supervised fine-tuning (SFT) and reinforcement learning (RL) is the standard paradigm for aligning large language models, yet fixed mixing schedules…
Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
We formalize Rollout Informativeness under a Fixed Budget (RIFB) as the expected non-vanishing policy-gradient mass that a tool-use rollout set injects into Group Relative Policy O…
AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
Agent-repair leaderboards reorder under evaluator reconfiguration, and a measurable share of the reordering is produced by methods that consult evaluator-derived signal during inte…
Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair
Yuelin Hu, Zhenbo Yu, Zhengxue Cheng +2
Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam as a neutral backend. We show this composition ha…
WebExpert: domain-aware web agents with critic-guided expert experience for high-precision search
Yuelin Hu, Zhengxue Cheng, Ronghua Wu +5
Specialized web tasks in finance, biomedicine, and pharmaceuticals remain challenging due to missing domain priors: queries drift, evidence is noisy, and reasoning is brittle. We p…
Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models
Yuelin Hu, Zhengxue Cheng, Wei Liu +1
Hybrid training methods for large language models combine supervised fine tuning (SFT) on expert demonstrations with reinforcement learning (RL) on model rollouts, typically at the…
MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetings
Yuelin Hu, Jun Xu, Bingcong Lu +4
Enterprise meeting environments require AI assistants that handle diverse operational tasks, from rapid fact checking during live discussions to cross meeting analysis for strategi…
PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
Tingjia Miao, Wenkai Jin, Jinxin Tan +22
Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because research requires deep domain ex…
Rate-Aware Learned Speech Compression
Jun Xu, Zhengxue Cheng, Guangchuan Chi +3
The rapid rise of real-time communication and large language models has significantly increased the importance of speech compression. Deep learning-based neural speech codecs have…