SearchSkill: 教授大语言模型使用搜索工具与演进技能库
SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks
AI总结：
SearchSkill通过可重用的搜索技能显式规划查询，提升开放域问答中的检索效率和推理质量，改进了知识密集型问答基准的精确匹配表现。
摘要：
教授语言模型使用搜索工具不仅是是否搜索的问题，更是是否发出良好查询的问题。在开放域问答中，广泛或复制的查询常浪费检索预算并影响后续推理。我们提出\Ours框架，通过可重用的搜索技能显式规划查询。在每一步，模型首先选择技能，然后根据选定的技能卡生成搜索或回答动作。技能库本身并非固定：SearchSkill维护一个演进的SkillBank，从反复失败模式中扩展或细化它，并在监督训练前重建受影响的轨迹。所得到的两阶段SFT配方使训练与推理时技能选择后接技能基础执行的协议对齐。在开源和闭源模型上，SearchSkill提高了知识密集型问答基准的精确匹配表现，并产生了更好的检索行为，包括更少的复制首次查询、更多原子跳转聚焦查询以及在小检索预算内更多正确答案。这些结果表明，显式的技能条件查询规划是将搜索视为统一动作的轻量替代方案。
英文摘要：
Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especially important in open-domain question answering, where broad or copied queries often waste retrieval budget and derail later reasoning. We propose \Ours, a framework that makes query planning explicit through reusable search skills. At each step, the model first selects a skill, then generates a search or answer action conditioned on the selected skill card. The skill inventory itself is not fixed: SearchSkill maintains an evolving SkillBank, expands or refines it from recurrent failure patterns, and reconstructs affected trajectories before supervised training. The resulting two-stage SFT recipe aligns training with the inference-time protocol of skill selection followed by skill-grounded execution. Across open-source and closed-source models, SearchSkill improves exact match on knowledge-intensive QA benchmarks and yields better retrieval behavior, including fewer copied first queries, more atomic hop-focused queries, and more correct answers within a small search budget. These results suggest that explicit skill-conditioned query planning is a lightweight alternative to treating search as an undifferentiated action.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
