Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis

2026-05-12

AI Summary

Traditional static analysis struggles to incorporate external knowledge such as documentation and security advisories, while large language models (LLMs), despite their capacity for information integration, often lack transparency and traceability in their reasoning. This work proposes an “agentic interpretation” framework that, for the first time, integrates lattice-based static analysis theory into LLM-driven program reasoning. By modeling local program assertions using finite-height lattices and iteratively reconciling LLM judgments through a worklist algorithm, the approach establishes a structured analysis pipeline where evidence is traceable and conclusions are reconcilable. Empirical evaluation demonstrates that this method significantly enhances the reliability and interpretability of LLM-based program analysis, particularly when applied to codebases containing opaque third-party components.

Abstract

Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program analyses that depend on information beyond the source program, or that are otherwise not amenable to conventional static analyzers. However, directly asking an LLM for a one-shot whole-program analysis is brittle because it compresses many evidence-dependent judgments into a single opaque answer, rather than exposing which conclusions are supported or disputed and using intermediate findings to guide later, more focused searches. In this paper, we propose agentic interpretation, a framework that brings the discipline of lattice-based static analysis to LLM-driven program reasoning. At a high level, agentic interpretation decomposes a high-level analysis goal into localized claims, and tracks the LLM's judgment about each claim in a finite-height lattice. A worklist algorithm governs how claims and their judgments evolve during the analysis. We introduce a formal model of agentic interpretation, explore the design space it opens, and illustrate the approach with a worked example analyzing code that depends on opaque third-party components.

Problem

• program analysis
• large language models
• static analysis
• evidence-based reasoning
• interpretability

Innovation

• agentic interpretation
• lattice-based analysis
• LLM-driven program analysis
• worklist algorithm
• evidence decomposition