Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoning

arXiv:2604.10516v1 Announce Type: new Abstract: Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-augmented approaches rely primarily on lexical or embedding similarity, which is often a weak proxy for the task-critical knowledge needed for multi-step reasoning. In many such tasks, the relevant knowledge is not merely textually related to the query, but is instead grounded in executable code and the dependency structure through which computations are carried out. To address this mismatch, we propose SGKR (Structure-Grounded Knowledge Retrieval), a retrieval framework that organizes domain knowledge with a graph induced by function-call dependencies. Given a question, SGKR extracts semantic input and output tags, identifies dependency paths connecting them, and constructs a task-relevant subgraph. The associated knowledge and corresponding function implementations are then assembled as a structured context for LLM-based code generation. Experiments on multi-step data analysis benchmarks show that SGKR consistently improves solution correctness over no-retrieval and similarity-based retrieval baselines for both vanilla LLMs and coding agents.

Related

• OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning
• ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation
• ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding
• HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptation

Source: arXiv cs.CL | 2026-04-14