**范围：提升智能体效能的提示演进**

摘要

大型语言模型智能体正越来越多地被部署在产生海量动态情境的环境中。然而一个关键瓶颈依然存在：虽然智能体能够获取这些情境信息，但其静态提示词缺乏有效管理机制，导致校正性和增强性故障反复出现。为弥补这一能力缺口，我们提出了SCOPE（基于提示词进化的自演化情境优化）框架。该框架将情境管理构建为在线优化问题，通过综合分析执行轨迹生成指导原则，实现智能体提示词的自动化演进。我们设计了双流机制来平衡战术特异性（解决即时错误）与战略通用性（演进长期原则），并引入视角驱动探索机制以最大化策略覆盖范围，提升智能体针对特定任务具备正确策略的概率。在HLE基准测试上的实验表明，SCOPE框架将任务成功率从14.23%提升至38.64%且无需人工干预。项目代码已开源：https://github.com/JarvisPei/SCOPE。

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 SCOPE (Self-evolving Context Optimization via Prompt Evolution). SCOPE frames context management as an online optimization problem, synthesizing guidelines from execution traces to automatically evolve the agent's prompt. We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles). Furthermore, we introduce Perspective-Driven Exploration to maximize strategy coverage, increasing the likelihood that the agent has the correct strategy for any given task. 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.

范围：提升智能体效能的提示演进

SCOPE: Prompt Evolution for Enhancing Agent Effectiveness

摘要

Support