{"ID":2878520,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17905","arxiv_id":"2508.17905","title":"Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning","abstract":"Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods rely on task-specific strategies or bespoke representations, which hinder their ability to dismantle barriers between different SKR tasks, thereby constraining their overall performance in cross-task scenarios. In this paper, we introduce \\textsc{Pandora}, a novel USKR framework that addresses the limitations of existing methods by leveraging two key innovations. First, we propose a code-based unified knowledge representation using \\textsc{Python}'s \\textsc{Pandas} API, which aligns seamlessly with the pre-training of LLMs. This representation facilitates a cohesive approach to handling different structured knowledge sources. Building on this foundation, we employ knowledge transfer to bolster the unified reasoning process of LLMs by automatically building cross-task memory. By adaptively correcting reasoning using feedback from code execution, \\textsc{Pandora} showcases impressive unified reasoning capabilities. Extensive experiments on six widely used benchmarks across three SKR tasks demonstrate that \\textsc{Pandora} outperforms existing unified reasoning frameworks and competes effectively with task-specific methods.","short_abstract":"Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods rely on task-specific strategies or bespoke representations, which hinder their ability to dismantle barriers betwee...","url_abs":"https://arxiv.org/abs/2508.17905","url_pdf":"https://arxiv.org/pdf/2508.17905v1","authors":"[\"Yongrui Chen\",\"Junhao He\",\"Linbo Fu\",\"Shenyu Zhang\",\"Rihui Jin\",\"Xinbang Dai\",\"Jiaqi Li\",\"Dehai Min\",\"Nan Hu\",\"Yuxin Zhang\",\"Guilin Qi\",\"Yi Huang\",\"Tongtong Wu\"]","published":"2025-08-25T11:22:58Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}