ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Jun Zhang, Jiasheng Zheng, Boxi Cao, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun
• Venue: arXiv: cs.CL
• Published: 2026-06-22
• Collected: 2026-06-23
• URL: http://arxiv.org/abs/2606.23404v1
• PDF: https://arxiv.org/pdf/2606.23404v1
• DOI: UNKNOWN

Plain-Language Brief

The paper introduces ReasoningLens, an open-source framework designed to help with the visualization and diagnostic auditing of complex reasoning chains in large reasoning models. The tool aims to address the issue of long Chain-of-Thought traces by structuring them into interactive hierarchies, using automated error detection, and synthesizing systemic reasoning profiles.

What the Document Says

• The paper presents ReasoningLens, an open-source framework for the hierarchical visualization and diagnostic auditing of complex reasoning chains in large reasoning models.
• ReasoningLens aims to address information necropsy by structuring traces into interactive hierarchies, leveraging an agentic auditor for automated error detection, and synthesizing systemic reasoning profiles.
• The tool is designed to reveal model-specific blind spots and transform unstructured walls of text into actionable insights.

Key Concepts Mentioned

• Large Reasoning Models
• Chain-of-Thought traces
• ReasoningLens
• Hierarchical visualization
• Diagnostic auditing
• Interactive hierarchies
• Agentic auditor

Claims Made by the Document

• The emergence of Large Reasoning Models has created a transparency burden.
• ReasoningLens can address this transparency burden by structuring traces, leveraging an agentic auditor, and synthesizing systemic reasoning profiles.

Evidence Used

• The text states that large reasoning models produce exceptionally long Chain-of-Thought traces which bury critical logic under massive procedural text.
• The paper claims that ReasoningLens addresses this issue by providing a framework for hierarchical visualization and diagnostic auditing.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.