让复杂推理过程可看可查，发现模型逻辑漏洞
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
- 分层可视化推理链条，区分策略与执行细节
- 自动检测错误并用工具验证，提升诊断效率
- 揭示模型固有盲点，适合调试与优化推理模型
大型推理模型产生极长的思维链，导致关键逻辑被冗长文本掩盖。为此，我们提出开源框架 ReasoningLens，实现复杂推理链的分层可视化与诊断审计。该框架通过：(1) 将思维链结构化为可交互的层级，分离高层策略与底层执行；(2) 利用代理式审计器实现自动错误检测与工具增强验证；(3) 构建系统性推理画像，揭示模型特有的认知盲区。通过将无序文本转化为可操作洞察，ReasoningLens为解释、调试与优化下一代推理型AI提供了模块化基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。