Auriga:以治理框架控制 LLM 代理,優化先執行後驗證許可制區塊鏈的有效吞吐量
Auriga: Harness-Governed LLM Agents for Effective Throughput Optimization in Execute-Order-Validate Permissioned Blockchains
研究速讀
這篇論文提出 Auriga,一個非侵入式框架,同時優化先執行後驗證區塊鏈的原始吞吐量與交易成功率。它用受治理框架控制的多代理 LLM 架構搜尋配置,並在執行前以 AST 模板預測讀寫集、劃分無衝突交易群組。作者稱在三個基準、衝突率最高 70% 下,有效吞吐量較預設 Fabric 最多提升 6.0 倍。
值得留意
- 以受治理框架控制的多代理 LLM 架構進行樣本效率高的配置搜尋與飽和感知評估
- 離線以 LLM 從智慧合約擷取符號 AST 模板,執行時預測讀寫集並劃分無衝突群組
- 作者稱在三個基準、衝突率最高 70% 下,有效吞吐量較預設 Fabric 最多提升 6.0 倍、較最強基線提升 2.0 倍
閱讀限制
僅閱讀標題與摘要,未檢視全文、實驗設定或同儕審查狀態;效能數字與參數相依性發現均為作者陳述,未經獨立驗證。
原始摘要 [EN]
Effective throughput, the product of raw throughput and transaction success rate, determines the useful capacity of Execute-Order-Validate blockchains such as Hyperledger Fabric. Most prior work either tunes configurations to raise raw throughput, requiring many costly redeployments, or controls conflicts to raise the success rate, repairing them only after execution with kernel modifications. The few joint approaches tune only a small set of parameters and still rely on kernel changes to resolve conflicts. To address these challenges, we present Auriga, a non-invasive framework that jointly optimizes both factors through sample-efficient LLM-guided configuration search and pre-execution conflict prevention. A harness-governed multi-agent architecture coordinates LLM agents for parameter exploration, saturation-aware evaluation, and experience consolidation, with the harness controlling tool and memory access and retaining termination authority. For transaction scheduling, an LLM extracts symbolic AST templates from smart contracts offline. At runtime, the scheduler predicts read-write sets without executing them and partitions transactions into conflict-free groups. Across three benchmarks and conflict rates up to 70%, Auriga improves effective throughput by up to 6.0 times over default Fabric and 2.0 times over the strongest baseline. The tuning agent also discovers undocumented parameter dependencies, and ablation studies show the independent contributions of both subsystems.
AI 摘要僅根據公開標題與摘要整理;研究結論來自作者,請以原文為準。