FORT-Searcher: 合成抗捷径的搜索任务以训练深度搜索代理

摘要

训练深度搜索代理需要可验证的问题，其答案只有在通过搜索获取足够证据后才能获得。现有的合成方法通常通过丰富图结构来增加表面难度，但单纯的结构复杂性并不能保证实现实际的搜索难度：目标搜索过程可能通过一条更简单的识别路径而崩溃。我们通过一个捷径感知的难度框架形式化了这一差距，并识别出四种可行的捷径风险：证据共覆盖、单线索选择性、暴露常量以及先验知识绑定。为诊断其实际影响，我们使用轨迹特征，包括求解成本、答案命中时间以及先验捷径率。在框架指导下，我们提出了FORT——一种抗捷径训练数据合成框架。FORT通过控制实体选择、证据图构建、问题表述和对抗性优化中的捷径风险，构建抗捷径的训练数据。实验表明，与现有的开源深度搜索数据集相比，FORT能诱导更长的搜索前探索时间，并减少捷径模式。利用生成的轨迹，我们仅通过监督微调训练了FORT-Searcher，在具有挑战性的深度搜索基准测试中，它在同规模开源搜索代理中取得了最佳整体性能。相关资源将在https://github.com/RUCAIBox/FORT-Searcher 上提供。

English

Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis methods often increase apparent difficulty by enriching graph structures, but structural complexity alone does not guarantee realized search difficulty: the intended search process can collapse through a cheaper identifying route. We formalize this gap with a shortcut-aware difficulty framework and identify four actionable shortcut risks: evidence co-coverage, single-clue selectivity, exposed constants, and prior-knowledge binding. To diagnose their realized effects, we use trajectory signatures including solving cost, answer hit time, and prior-shortcut rate. Guided by this framework, we introduce FORT, a Framework of Shortcut-Resistant Training-Data Synthesis. FORT constructs shortcut-resistant training data by controlling shortcut risks across entity selection, evidence graph construction, question formulation, and adversarial refinement. Experiments show that FORT induces longer pre-answer search and fewer shortcut patterns than existing open-source deep search datasets. Using the resulting trajectories, we train FORT-Searcher with supervised fine-tuning (SFT) only, and it achieves the best overall performance among comparable-size open-source search agents on challenging deep search benchmarks. Relevant resources will be made available at https://github.com/RUCAIBox/FORT-Searcher.