8 papers
Group-Reflective Self-Distillation for Agentic Reinforcement Learning
Binbin Zheng, Zijun Xie, Guanqun Zhao +4
Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervis…
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
Binbin Zheng, Xing Ma, Yiheng Liang +6
On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit as…
PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
Ai Jian, Jingqing Ruan, Xing Ma +5
Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large language models (LLMs) with human…
Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems
Xuxin Cheng, Ke Zeng, Zhiquan Cao +65
Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language…
Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
Xiaoyun Zhang, Jingqing Ruan, Xing Ma +4
Detecting abnormal events in real-world customer service dialogues is highly challenging due to the complexity of business data and the dynamic nature of customer interactions. Mor…
BootSeer: Analyzing and Mitigating Initialization Bottlenecks in Large-Scale LLM Training
Rui Li, Xiaoyun Zhi, Jinxin Chi +14
Large Language Models (LLMs) have become a cornerstone of modern AI, driving breakthroughs in natural language processing and expanding into multimodal jobs involving images, audio…
Tackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable Aggregation
Xing Ma
Federated learning aims to train a global model in a distributed environment that is close to the performance of centralized training. However, issues such as client label skew, da…
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
Xiaoyun Zhang, Jingqing Ruan, Xing Ma +6
Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning, especially on s…