14 papers
MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory
Beidi Zhao, Yaoqi Chen, Yuru Feng +10
Long-horizon agents accumulate trajectories spanning hundreds of interleaved reasoning, action, and observation steps, where answering a query may depend on evidence buried far bac…
DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System
Yizou Chen, Tsun-Yu Yang, Zhisheng Hu +2
Traditional graph processing systems are built on monolithic servers, which couple a fixed ratio of compute and memory resources but often result in resource under-utilization in d…
Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
Yaoqi Chen, Haibin Lai, Yuru Feng +12
LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade. Existing R…
Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
Zihan Zhao, Baotong Lu, Shengjie Lin +8
Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent s…
RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
Yaoqi Chen, Jinkai Zhang, Baotong Lu +16
Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because t…
Towards Robustness: A Critique of Current Vector Database Assessments
Zikai Wang, Qianxi Zhang, Baotong Lu +2
Vector databases are critical infrastructure in AI systems, and average recall is the dominant metric for their evaluation. Both users and researchers rely on it to choose and opti…