5 papers
MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
Songxin Lei, Kun Ouyang, Weilin Ruan +4
Long-horizon LLM agents require memory systems that recover useful evidence from large interaction histories without passing excessive context to downstream models. Existing memory…
Reinforcement Learning for Delivery Drone-Based Participatory Sensing in Dynamic Environments
Xin Ouyang, Songxin Lei, Xusen Guo +3
Using Unmanned Aerial Vehicle (UAV) for urban sensing has emerged as a powerful paradigm to monitor the status of the city, e.g., air quality and noise levels, through agile aerial…
Hierarchical Reinforcement Learning for Cooperative Air-Ground Delivery in Urban System
Songxin Lei, Chunming Ma, Haomin Wen +7
Cooperative air-ground delivery has emerged as a promising logistics paradigm by leveraging the complementary strengths of UAVs and ground carriers. However, effective dispatching…
A Game-Theoretic Spatio-Temporal Reinforcement Learning Framework for Collaborative Public Resource Allocation
Songxin Lei, Qiongyan Wang, Yanchen Zhu +6
Public resource allocation involves the efficient distribution of resources, including urban infrastructure, energy, and transportation, to effectively meet societal demands. Howev…
Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential Mitigations
Yiming Huang, Biquan Bie, Zuqiu Na +4
The rise of Large Language Models (LLMs) like ChatGPT has advanced natural language processing, yet concerns about cognitive biases are growing. In this paper, we investigate the a…