5 papers
Learning to Wait: Synchronizing Agents with the Physical World
Yifei She, Ping Zhang, He Liu +6
Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental \textit{Temporal G…
ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
Qiaoling Chen, Zijun Liu, Peng Sun +6
Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative d…
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
Zhiheng Xi, Xin Guo, Yang Nan +18
Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale…
Metadata-Guided Adaptable Frequency Scaling across Heterogeneous Applications and Devices
Jinqi Yan, Fang He, Qianlong Sang +5
Dynamic Voltage and Frequency Scaling is essential for enhancing energy efficiency in mobile platforms. However, traditional heuristic-based governors are increasingly inadequate f…
Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving
Ziming Liu, Boyu Tian, Guoteng Wang +15
Mixture-of-Experts (MoE) models challenge serving infrastructures with dynamic, sparse expert utilization, causing instability on conventional systems designed for dense architectu…