ReasoningFlow: Semantic Structure of Complex Reasoning Traces
Jinu Lee, Sagnik Mukherjee, Dilek Hakkani-Tur, Julia Hockenmaier
TL;DR
ReasoningFlow provides a unified, interpretable schema for analyzing the complex reasoning traces of large reasoning models, enabling better understanding and evaluation of their reasoning processes.
Contribution
It introduces a novel schema that parses reasoning traces into directed acyclic graphs, capturing semantic structures and reasoning patterns.
Findings
Enables characterization of reasoning patterns as subgraph structures
Facilitates understanding and evaluation of reasoning traces
Offers a human-interpretable representation of complex reasoning
Abstract
Large reasoning models (LRMs) generate complex reasoning traces with planning, reflection, verification, and backtracking. In this work, we introduce ReasoningFlow, a unified schema for analyzing the semantic structures of these complex traces. ReasoningFlow parses traces into directed acyclic graphs, enabling the characterization of distinct reasoning patterns as subgraph structures. This human-interpretable representation offers promising applications in understanding, evaluating, and enhancing the reasoning processes of LRMs.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsSemantic Web and Ontologies · Logic, Reasoning, and Knowledge · AI-based Problem Solving and Planning