EPOCH: An Agentic Protocol for Multi-Round System Optimization
This addresses the problem of fragmented optimization approaches for autonomous agents in production workflows, though it appears incremental as a protocol built on existing concepts.
The paper tackles the lack of a unified protocol for multi-round autonomous system optimization by introducing EPOCH, which organizes optimization into baseline construction and iterative self-improvement phases with standardized stages and tracking, enabling coordinated optimization across various components while preserving stability and reproducibility.
Autonomous agents are increasingly used to improve prompts, code, and machine learning systems through iterative execution and feedback. Yet existing approaches are usually designed as task-specific optimization loops rather than as a unified protocol for establishing baselines and managing tracked multi-round self-improvement. We introduce EPOCH, an engineering protocol for multi-round system optimization in heterogeneous environments. EPOCH organizes optimization into two phases: baseline construction and iterative self-improvement. It further structures each round through role-constrained stages that separate planning, implementation, and evaluation, and standardizes execution through canonical command interfaces and round-level tracking. This design enables coordinated optimization across prompts, model configurations, code, and rule-based components while preserving stability, reproducibility, traceability, and integrity of evaluation. Empirical studies in various tasks illustrate the practicality of EPOCH for production-oriented autonomous improvement workflows.