activity
20242026
most citedWhy Database Manuals Are Not Enough: Efficient and Reliable Configuration Tuning for DBMSs via Code-Driven LLM Agents

3 citations · 3 across the 14 of their papers we have counts for

collaborators

19 papers

cs.DB2026

DBRepro: Automated Database Synthesis via a Hybrid Constraint-Solving Approach for Reproducing Slow Queries

Zhaoyang Zhang, Shuang Liu, Dengfeng Xu +4

Slow queries frequently cause severe performance bottlenecks in database management systems. Diagnosing their root causes online risks exacerbating resource contention, while data…

cs.DB2026

DBcover: A White-box SQL Test Generation Framework for Coverage Improvement

Yankai Rong, Shuang Liu, Jinhao Dong +4

Relational Database Management Systems (RDBMSs) are the backbone of modern data-intensive applications, making reliability and robustness critical. However, achieving high coverage…

cs.DB2026

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…

cs.DB2026

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…

cs.LG2026

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…

cs.CL2026

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…