4 papers
AReaL-DTE: Sparse Policy-Weight Transfer for Online Agentic Reinforcement Learning
Yingqi Peng, Jiawei Zhang, Wenhao Zhou +7
Online agentic reinforcement learning implemented with micro-services separates policy training from rollout generation, improving scalability and modularity while potentially maki…
Online Resource Allocation with Continuous Random Consumption: Regret under Degeneracy
Jiawei Zhang
We study online resource allocation when both rewards and consumption sizes may be continuously distributed. Requests arrive sequentially and must be accepted or rejected irrevocab…
Tight Lower Bounds for the Multi-Secretary Problem via Bellman Certificates
Jiawei Zhang
This paper studies additive regret in the multi-secretary problem, defined as the gap between the expected offline prophet reward and the reward of the best online policy. Prior wo…
Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents
Ran Yan, Wei Fu, Jiale Li +21
LLM agents are rapidly being deployed in production, including coding assistants, customer-support chatbots, and scientific research assistants, yet they remain fundamentally stati…