arXiv (All)
open access
Dissecting Hierarchical Reasoning Models: A Mechanistic Study
We study Hierarchical Reasoning Model (HRM), a representative hierarchical Transformer-based latent reasoning model with many variants, on Sudoku, Maze, and ARC-AGI-2. We mechanistically understand how HRM reasons and what information it encodes. Our analyses compare HRM against Transformer baseline
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs#986889
- Hierarchical Reasoning Model#1142544
- How Should Reasoning Be Organized in a Transformer's Latent Space?#1131657
- A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM#984715
- Ceiling of a Task: When Can a Transformer Succeed Without Its Chain of Thought?#1117846
Record · ID 1036880
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive