7 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…
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation
Yuru Feng, Yaoqi Chen, Beidi Zhao +7
Although agent skills equip LLMs with reusable procedural knowledge, manual maintenance suffers from high costs, unscalability, and misalignment. Real-world deployments thus requir…
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…
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…
Scalable Distributed Vector Search via Accuracy Preserving Index Construction
Yuming Xu, Qianxi Zhang, Qi Chen +8
Scaling Approximate Nearest Neighbor Search (ANNS) to billions of vectors requires distributed indexes that balance accuracy, latency, and throughput. Yet existing index designs st…