让大模型代理自动优化提示词，提升复杂任务成功率
SCOPE: Prompt Evolution for Enhancing Agent Effectiveness
- 将上下文管理视为在线优化问题，自动演化提示词
- 在HLE基准上任务成功率达38.64%，远超原始14.23%
- 适合需要持续自适应的智能代理系统开发者
大型语言模型（LLM）代理被广泛应用于生成海量动态上下文的环境，但其静态提示词缺乏有效管理上下文的能力，导致反复出现修正与增强失败。为此，我们提出通过提示词演化实现自我演化的上下文优化方法（SCOPE）。SCOPE将上下文管理建模为在线优化问题，从执行轨迹中提取指导原则，自动演化代理提示词。提出双流机制，将指导原则在战术记忆（即时纠错）和战略记忆（持续优化）间流转，通过冲突解决、包含剪枝和整合不断优化战略记忆。为扩大策略覆盖，采用视角驱动探索，同时演化多个不同优化视角的提示词。在HLE基准测试中，无需人工干预，任务成功率从14.23%提升至38.64%。代码已开源。
原文摘要 · Abstract (English)
Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts. However, a critical bottleneck remains: while agents have access to this context, their static prompts lack the mechanisms to manage it effectively, leading to recurring Corrective and Enhancement failures. To address this capability gap, we introduce Self-evolving Context Optimization via Prompt Evolution (SCOPE). SCOPE frames context management as an \textit{online optimization} problem, synthesizing guidelines from execution traces to automatically evolve the agent's prompt. We propose a Dual-Stream mechanism that routes guidelines between tactical memory (immediate error correction) and strategic memory, which is continuously refined through conflict resolution, subsumption pruning, and consolidation. To maximize strategy coverage, Perspective-Driven Exploration evolves multiple parallel prompts guided by distinct optimization perspectives. Experiments on the HLE benchmark show that SCOPE improves task success rates from 14.23\% to 38.64\% without human intervention. We make our code publicly available at https://github.com/JarvisPei/SCOPE.
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。