Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Ted Cruz AI bill could let firms bribe Trump to avoid safety laws, critics warn

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning – Takara TLDR

China reportedly discouraged purchase of NVIDIA AI chips due to ‘insulting’ Lutnick statements

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Business AI
    • Advanced AI News Features
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Hugging Face

Paper page – Chain-of-Thought Tokens are Computer Program Variables

By Advanced AI EditorMay 10, 2025No Comments1 Min Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Chain-of-thoughts (CoT) requires large language models (LLMs) to generate
intermediate steps before reaching the final answer, and has been proven
effective to help LLMs solve complex reasoning tasks. However, the inner
mechanism of CoT still remains largely unclear. In this paper, we empirically
study the role of CoT tokens in LLMs on two compositional tasks: multi-digit
multiplication and dynamic programming. While CoT is essential for solving
these problems, we find that preserving only tokens that store intermediate
results would achieve comparable performance. Furthermore, we observe that
storing intermediate results in an alternative latent form will not affect
model performance. We also randomly intervene some values in CoT, and notice
that subsequent CoT tokens and the final answer would change correspondingly.
These findings suggest that CoT tokens may function like variables in computer
programs but with potential drawbacks like unintended shortcuts and
computational complexity limits between tokens. The code and data are available
at https://github.com/solitaryzero/CoTs_are_Variables.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleJames Cameron Wants To Use AI To “Cut The Cost” Of Filmmaking
Next Article Nvidia to launch downgraded H20 AI chip for China: Report
Advanced AI Editor
  • Website

Related Posts

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning – Takara TLDR

September 11, 2025

Hunyuan-MT Technical Report – Takara TLDR

September 11, 2025

3D and 4D World Modeling: A Survey – Takara TLDR

September 11, 2025
Leave A Reply

Latest Posts

Sally Mann Says Her Black Men Photos Are ‘Problematic’ in Hindsight

National Gallery and Tate Have ‘Bad Blood’—and More Art News

Christie’s Will Auction The First Calculating Machine In History

The Art Market Isn’t Dying. The Way We Write About It Might Be.

Latest Posts

Ted Cruz AI bill could let firms bribe Trump to avoid safety laws, critics warn

September 11, 2025

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning – Takara TLDR

September 11, 2025

China reportedly discouraged purchase of NVIDIA AI chips due to ‘insulting’ Lutnick statements

September 11, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Ted Cruz AI bill could let firms bribe Trump to avoid safety laws, critics warn
  • AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning – Takara TLDR
  • China reportedly discouraged purchase of NVIDIA AI chips due to ‘insulting’ Lutnick statements
  • Tool-space interference in the MCP era: Designing for agent compatibility at scale
  • Sally Mann Says Her Black Men Photos Are ‘Problematic’ in Hindsight

Recent Comments

  1. JamesMub on Chinese Firms Have Placed $16B in Orders for Nvidia’s (NVDA) H20 AI Chips
  2. Lamartex on Chinese Firms Have Placed $16B in Orders for Nvidia’s (NVDA) H20 AI Chips
  3. JamesMub on Anthropic’s popular Claude Code AI tool now included in its $20/month Pro plan
  4. Lamartex on Anthropic’s popular Claude Code AI tool now included in its $20/month Pro plan
  5. RichardBub on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.