EPOCH让系统自动多轮优化，统一管理改进流程。
EPOCH: An Agentic Protocol for Multi-Round System Optimization
- 分两阶段：先建基线，再迭代自改进
- 每轮分规划、实现、评估三步，分工明确
- 适合需要稳定可复现优化的工程场景
自主代理正被广泛用于通过迭代执行与反馈来优化提示词、代码和机器学习系统。然而现有方法通常局限于特定任务的优化循环，而非统一协议以建立基准并管理多轮自改进。本文提出EPOCH，一种面向异构环境的多轮系统优化工程协议。EPOCH将优化分为基线构建与迭代自改进两个阶段，并在每轮中通过角色约束的阶段划分，分离规划、实施与评估环节，通过标准化命令接口和轮次级追踪实现统一执行。该设计支持提示词、模型配置、代码及规则组件的协同优化，同时保障稳定性、可复现性、可追溯性与评估完整性。多种任务的实证研究验证了EPOCH在生产级自主改进工作流中的实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。