在技能检索前提供及时指导：在智能体上下文中保留有用的预热提示
Enabling Timely Guidance before Skill Retrieval: Retaining Helpful Warm Tips in Agent Context
浏览论文内容
中文总结 AI 辅助
针对智能体技能检索前缺乏指导的问题，提出TipsWarm机制，通过预算化预热提示池选择性注入上下文，在控制维护成本的同时提升任务成功率。
中文摘要 AI 辅助
可复用技能帮助基于大语言模型的智能体解决复杂任务，但智能体必须在承诺采用低效方法之前获得指导。现有技能机制通常仅暴露元数据并按需加载完整内容，导致在智能体决定检索之前无法获得有用的指导。通用记忆方法可能产生大量维护开销，而将指导保留在对话上下文中则可能使智能体反复暴露于无关或有害的建议。我们提出TipsWarm机制，通过维护一个预算有限的技能派生关键点池（即“预热提示”），用于选择性注入每一轮消息的上下文中，从而补充现有技能机制。通过将事件触发的LLM评估与廉价的逐轮筛选分离，它使可迁移的技能指导随时可用，同时控制维护成本。在三个编码和迭代任务执行基准测试中，与最近的技能和通用记忆基线相比，TipsWarm在保持时间效率的同时实现了最高的任务成功率。
英文摘要
Reusable skills help LLM-based agents solve complex tasks, but the agent must receive guidance before it commits to an ineffective approach. Existing skill mechanisms often expose only metadata and load full content on demand, leaving useful guidance unavailable until the agent decides to retrieve it. General memory methods can incur substantial maintenance overhead, while keeping guidance in conversation context risks repeatedly exposing the agent to irrelevant or harmful advice. We propose TipsWarm, a mechanism that complements existing skill mechanisms by maintaining a budgeted pool of skill-derived keypoints, or \textit{warm tips}, for selective injection into the context of every message turn. By separating event-triggered LLM assessment from inexpensive per-turn screening, it makes transferable skill guidance readily available while controlling maintenance costs. In three coding and iterative task-execution benchmarks, TipsWarm achieves the highest task success rate while remaining time-efficient, compared to recent skill and general memory baselines.
