AI 中文总结
本文提出潜在等价学习框架，通过身份分解和查询条件化路由，使数据代理在复杂企业数据环境中高效组织证据，在Data Agent Benchmark上以94.67%的Pass@1大幅超越基准。
AI 中文摘要
企业环境中的结构化数据代理必须对复杂的数据环境进行推理，这些环境中相关证据分布在模式、关系、策略和重复出现的业务角色中。现代代理系统通常通过可复用的Markdown风格记忆或技能文件来应对这一负担，这些文件保留先前发现的信息以供后续查询使用，从而减少重复发现相同结构的需要。这很有用，但它掩盖了一种自然的劳动分工：代理擅长语义推理，而学习系统擅长预测和组织重复出现的结构。我们引入潜在等价学习来弥合这一差距。该框架将持久的任务相关身份与其数据集相关的实现分开。在我们的实现中，支持和反对证据塑造了支持实现的Gaussian原型，这些原型学习这些身份在特定数据环境中如何表达，而软成员档案则保留了在硬分配下丢失的区分。一个单独的学习查询-原型系统表示重复出现的证据需求，并通过学习到的兼容性函数将它们映射到相同的持久身份结构中。这种身份分解、查询条件化的路由为下游推理物化了相关的数据集特定证据，使代理能够在已经组织的证据状态上操作，而不是在每次查询时重建跨模式结构。在Data Agent Benchmark上，涵盖12个异构数据集的54个查询，我们的完整实现在五次完整试验中实现了94.67%的数据集宏分层Pass@1和258/270次成功的原始查询尝试，而基准的Claude Opus 4.6参考代理为55.51%，在提交时排名40个排行榜条目中的第一。
英文摘要
Structured-data agents in enterprise settings must reason over complex data environments whose relevant evidence is distributed across schemas, relationships, policies, and recurring business roles. Modern agentic systems often address this burden through reusable markdown-style memory or skill files that preserve previously discovered information for later queries, reducing the need to rediscover the same structure repeatedly. This is useful, but it obscures a natural division of labor: agents are well suited to semantic reasoning, while learned systems are well suited to predicting and organizing recurring structure. We introduce latent equivalence learning to bridge this gap. The framework separates persistent task-relevant identities from their dataset-relative realizations. In our realization, supporting and opposing evidence shape support-realized Gaussian prototypes that learn how those identities are expressed in a particular data environment, while soft-membership profiles retain distinctions lost under a hard assignment. A separate learned query-prototype system represents recurring evidential requirements and maps them through a learned compatibility function into the same persistent identity structure. This identity-factorized, query-conditioned routing materializes the relevant dataset-specific evidence for downstream reasoning, allowing the agent to operate over an already organized evidential state rather than reconstructing cross-schema structure at every query. On the Data Agent Benchmark, spanning 54 queries across 12 heterogeneous datasets, our full implementation achieves 94.67% dataset-macro stratified Pass@1 over five complete trials and 258/270 successful raw query attempts, compared with 55.51% for the benchmark's Claude Opus 4.6 reference agent, ranking first among 40 leaderboard entries at submission.
