Search papers, labs, and topics across Lattice.
The paper introduces SAAS, a reinforcement learning framework to mitigate over-searching in agentic LLM search systems by improving self-awareness of knowledge boundaries. SAAS uses a search boundary modeling mechanism to identify when search is unnecessary, a boundary-aware reward to penalize over-searching, and a stage-wise optimization strategy to prioritize reasoning. Experiments show SAAS significantly reduces over-search without sacrificing accuracy, addressing a key inefficiency in agentic search.
Agentic LLMs waste cycles on unnecessary searches because they don't know what they already know, but SAAS teaches them to be more self-aware and cut the needless searching.
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.
