Auriga: Harness-Governed LLM Agents for Effective Throughput Optimization in Execute-Order-Validate Permissioned Blockchains
THE QUICK READ
The paper presents Auriga, a non-invasive framework that jointly optimizes raw throughput and transaction success rate in Execute-Order-Validate blockchains such as Hyperledger Fabric. A harness-governed multi-agent LLM architecture handles configuration search, saturation-aware evaluation, and experience consolidation, while an offline LLM extracts symbolic AST templates so a runtime scheduler can predict read-write sets and partition transactions into conflict-free groups before execution.
KEY POINTS
- Harness-governed multi-agent LLM architecture coordinates parameter exploration, saturation-aware evaluation, and experience consolidation
- Offline LLM extracts symbolic AST templates from smart contracts; the runtime scheduler predicts read-write sets and partitions conflict-free groups
- Authors report up to 6.0x effective throughput over default Fabric and 2.0x over the strongest baseline across three benchmarks at conflict rates up to 70%
READING LIMITS
Based only on the title and abstract; the full paper, experimental setup, and peer-review status were not examined, and all performance figures and parameter-dependency findings are the authors' claims without independent verification.
Source abstract [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 summaries use public titles and abstracts only. Research claims belong to the authors; consult the original paper.