{"ID":2849366,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.25017","arxiv_id":"2510.25017","title":"StorageXTuner: An LLM Agent-Driven Automatic Tuning Framework for Heterogeneous Storage Systems","abstract":"Automatically configuring storage systems is hard: parameter spaces are large and conditions vary across workloads, deployments, and versions. Heuristic and ML tuners are often system specific, require manual glue, and degrade under changes. Recent LLM-based approaches help but usually treat tuning as a single-shot, system-specific task, which limits cross-system reuse, constrains exploration, and weakens validation. We present StorageXTuner, an LLM agent-driven auto-tuning framework for heterogeneous storage engines. StorageXTuner separates concerns across four agents - Executor (sandboxed benchmarking), Extractor (performance digest), Searcher (insight-guided configuration exploration), and Reflector (insight generation and management). The design couples an insight-driven tree search with layered memory that promotes empirically validated insights and employs lightweight checkers to guard against unsafe actions. We implement a prototype and evaluate it on RocksDB, LevelDB, CacheLib, and MySQL InnoDB with YCSB, MixGraph, and TPC-H/C. Relative to out-of-the-box settings and to ELMo-Tune, StorageXTuner reaches up to 575% and 111% higher throughput, reduces p99 latency by as much as 88% and 56%, and converges with fewer trials.","short_abstract":"Automatically configuring storage systems is hard: parameter spaces are large and conditions vary across workloads, deployments, and versions. Heuristic and ML tuners are often system specific, require manual glue, and degrade under changes. Recent LLM-based approaches help but usually treat tuning as a single-shot, sy...","url_abs":"https://arxiv.org/abs/2510.25017","url_pdf":"https://arxiv.org/pdf/2510.25017v1","authors":"[\"Qi Lin\",\"Zhenyu Zhang\",\"Viraj Thakkar\",\"Zhenjie Sun\",\"Mai Zheng\",\"Zhichao Cao\"]","published":"2025-10-28T22:33:14Z","proceeding":"cs.DB","tasks":"[\"cs.DB\",\"cs.AI\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"LoRA\"]","has_code":false}