<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/iEZspXdcm" -->

---
title: [2611.17309] Classical Energies Learn to Reason 1,000x...
description: A learned version of Hopfield and Tank's 1980s energy function, termed CRAM, trains far faster than looped reasoning models on Sudoku-Extreme and Maze-Unique...
canonical: https://daily.dev/posts/iezspxdcm
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: [2611.17309] Classical Energies Learn to Reason 1,000x Faster than Looped Models | daily.dev
og:description: A learned version of Hopfield and Tank's 1980s energy function, termed CRAM, trains far faster than looped reasoning models on Sudoku-Extreme and Maze-Unique...
og:url: https://daily.dev/posts/iezspxdcm
og:image: https://api.daily.dev/og/posts/iEZspXdcm.png
og:image:alt: Post cover image
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# [2611.17309] Classical Energies Learn to Reason 1,000x Faster than Looped Models

**[Build With GenAI](https://daily.dev/sources/buildwithgenai)** · [@minhchienvu](https://daily.dev/minhchienvu) · 7 upvotes · 0 comments

## Summary

A learned version of Hopfield and Tank's 1980s energy function, termed CRAM, trains far faster than looped reasoning models on Sudoku-Extreme and Maze-Unique puzzles. CRAM solves 99.996% of Sudoku-Extreme and 100% of Maze-Unique test puzzles after 42 ms and 132 ms of training on one GPU. That's at least 1,000x faster than looped models on these tasks. It also matches baseline looped models at their highest accuracy on Sudoku-Extreme while using at least 282x fewer inference FLOPs. The authors argue energy descent gives built-in early stopping, adaptive compute, and interpretable weights, and cautions against trivially solvable benchmarks like Sudoku and Maze for testing looped reasoning scalability.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://arxiv.org/abs/2611.17309>

## Similar posts on daily.dev

- [How to Build Models Without Language, with Logical Intelligence](https://daily.dev/posts/how-to-build-models-without-language-with-logical-intelligence-ii06zfny1) · ByteByteGo · 26 upvotes · 3 comments
- [How Can A Model 10,000× Smaller Outsmart ChatGPT?](https://daily.dev/posts/how-can-a-model-10-000-smaller-outsmart-chatgpt--rgks7qbfm) · Towards Data Science · 9 upvotes · 0 comments
- [Overcoming the Twin Traps of AI](https://daily.dev/posts/overcoming-the-twin-traps-of-ai-sxcsxrcnj) · SD Times · 2 upvotes · 0 comments

---

Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#llm](https://daily.dev/tags/llm)

[View this post on daily.dev](https://daily.dev/posts/iezspxdcm)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/iezspxdcm","headline":"[2611.17309] Classical Energies Learn to Reason 1,000x Faster than Looped Models","text":"Shared: [2611.17309] Classical Energies Learn to Reason 1,000x Faster than Looped Models","url":"https://daily.dev/posts/iezspxdcm","datePublished":"2026-11-17T05:32:08.371Z","dateModified":"2026-11-17T05:43:47.405Z","author":{"@type":"Person","name":"Antonio","url":"https://daily.dev/minhchienvu","image":"https://media.daily.dev/image/upload/s--s0zG1uBh--/f_auto/v1751516662/avatars/avatar_gvAzfyIlv3WZNzsaddV7o?_a=BAMClqZW0","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":3590}},"image":"https://media.daily.dev/image/upload/s--qPvKM23u--/f_auto/v1722860399/public/Placeholder%2009","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":7},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/ocp4eu91q"},"isPartOf":{"@type":"WebPage","url":"https://daily.dev/squads/buildwithgenai","name":"Build With GenAI"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Build With GenAI","item":"https://daily.dev/squads/buildwithgenai"},{"@type":"ListItem","position":3,"name":"[2611.17309] Classical Energies Learn to Reason 1,000x Faster than Looped Models"}]}
```

