arXiv (All)
open access
How Should Reasoning Be Organized in a Transformer's Latent Space?
Continuous reasoning has emerged as a promising way to improve reasoning in large language models (LLMs). Yet we still lack a clear principle for deciding what a latent state should preserve. Reasoning by superposition shows that a single latent state can encode several search alternatives and expan
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
- How Many Thoughts Can a Vector Hold? The Capacity of Reasoning by Superposition#1083251
- What are Key Factors for Updates in RL for LLM Reasoning?#1036727
- Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs#1154670
- Evidence-Inference Reconstruction: When The Evidence Is Recalled But The Reasoning Goes Wrong#1118851
- Dissecting Hierarchical Reasoning Models: A Mechanistic Study#1036880
Record · ID 1131657
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