ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
For AI researchers and developers, this framework addresses the transparency burden of long reasoning traces, enabling better interpretation and debugging of reasoning-centric models.
ReasoningLens provides hierarchical visualization and diagnostic auditing for large reasoning models, transforming long chain-of-thought traces into interactive hierarchies and automated error detection to reveal model-specific blind spots.
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.