15 papers
From Blind Search to Memory-Aware Evolution: Efficient DBMS Tuning via Collaborative Diagnosis and Utility-Aware Retrieval
Zhaoyan Hong, Yishen Sun, Xinyi Zhang +7
Modern DBMSs expose multiple configurable components (e.g., knobs, query hints, and indexes) that jointly determine query performance. Multi-component tuning is challenging due to…
TVA: A Version-aware Temporal Graph Storage System for Real-time Analytics
Wenhao Li, Zhanhao Zhao, Jinhao Dong +4
Analyzing temporal graphs can reveal valuable insights that are typically hidden in static graphs. Unfortunately, existing graph storage systems either lack native temporal support…
RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference
Wenhao Li, Jinhao Dong, Hailin Zhang +3
Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budge…
Scaling Agentic Capabilities via Grounded Interaction Synthesis
Wenhang Shi, Jinhao Dong, Yiren Chen +4
General agentic intelligence hinges on the ability to interact with diverse real-world tools to complete complex tasks, a capability fundamentally tied to the quality of interactio…
Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
Wenhang Shi, Yiren Chen, Shuqing Bian +5
While prompt engineering is instrumental in maximizing the capabilities of Large Language Models (LLMs) during inference, the role of prompts during training remains critically und…
Why Database Manuals Are Not Enough: Efficient and Reliable Configuration Tuning for DBMSs via Code-Driven LLM Agents
Xinyi Zhang, Tiantian Chen, Zhentao Han +9
Modern database management systems (DBMSs) expose hundreds of configuration knobs that critically influence performance. Existing automated tuning methods either adopt a data-drive…