Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their own knowledge boundaries, blindly triggering searches when internal knowledge suffices and failing to terminate search even when adequate evidence has been collected. The lack of self-awareness leads to severe \textbf{over-search}, incurring substantial inference latency and prohibitive computational cost. To this end, we propose SAAS, a novel RL framework designed to cultivate dynamic self-awareness that precisely regulates search behavior without compromising accuracy. SAAS introduces three key components: (i) a search boundary modeling mechanism, which identifies the search boundary under the evolving policy by contrasting search-disabled and search-enabled rollouts; (ii) a boundary-aware reward module, which translates this boundary awareness into trajectory-level penalties, suppressing unnecessary and redundant searches; and (iii) a stage-wise optimization strategy, which leverages a sequential curriculum to prioritize reasoning over search regularization, thereby avoiding reward hacking. Extensive experiments demonstrate that SAAS substantially reduces over-search, while maintaining accuracy. Our code and implementation details are released at https://github.com/XMUDeepLIT/SAAS.

翻译：智能体搜索使大语言模型能够通过迭代推理和外部搜索解决复杂的多跳问题。尽管效果显著，但这类系统在实践中常面临关键局限：智能体无法识别自身知识边界，在内部知识足够时盲目触发搜索，即便已收集充分证据仍未能终止搜索过程。这种自感知缺失导致严重的\textbf{过度搜索}现象，引发大量推理延迟与高昂计算成本。为此，我们提出SAAS——一种新型强化学习框架，旨在培养动态自感知能力以精确调控搜索行为且不损害准确性。SAAS包含三大核心组件：（1）搜索边界建模机制：通过对比禁用搜索与启用搜索的轨迹序列，在策略演化过程中识别搜索边界；（2）边界感知奖励模块：将边界感知转化为轨迹级惩罚，抑制不必要及冗余搜索；（3）分阶段优化策略：采用序列化课程学习优先强化推理能力再优化搜索正则化，从而规避奖励破解问题。大量实验表明，SAAS在保持准确性的同时显著减少了过度搜索。我们的代码及实现细节已开源至 https://github.com/XMUDeepLIT/SAAS。