ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
2026-06-22 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors created ReasoningLens, a tool to help understand and check very long step-by-step explanations made by large AI reasoning models. It organizes these long reasoning chains into easier-to-follow parts, automatically spots errors with the help of special checking agents, and summarizes common mistakes the model makes. This helps people see where the AI might go wrong and makes it easier to fix or improve its logic. Overall, the authors aim to make complex AI reasoning clearer and more manageable.
Large Reasoning ModelsChain-of-Thoughthierarchical visualizationerror detectiondiagnostic auditingagentic auditorreasoning profilesAI transparencytool-augmented verification
Authors
Jun Zhang, Jiasheng Zheng, Boxi Cao, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun
Abstract
The emergence of Large Reasoning Models has introduced exceptionally long Chain-of-Thought traces, creating a transparency burden where critical logic is often buried under massive procedural text. To address this, we present ReasoningLens, an open-source framework designed for the hierarchical visualization and diagnostic auditing of complex reasoning chains. ReasoningLens addresses information necropsy by: (1) structuring traces into interactive hierarchies that separate high-level strategy from low-level execution; (2) leveraging an agentic auditor for automated error detection and tool-augmented verification; and (3) synthesizing systemic reasoning profiles to reveal model-specific blind spots. By transforming unstructured walls of text into actionable insights, ReasoningLens provides a modular foundation for interpreting, debugging, and optimizing the next generation of reasoning-centric AI.