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

Client Pressure and the Widening AI Adoption Gap – Artificial Lawyer

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training – Takara TLDR

OpenAI launches Sora 2 with TikTok-style app

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

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones – Takara TLDR

By Advanced AI EditorOctober 1, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


Does RL teach LLMs genuinely new skills, or does it merely activate existing
ones? This question lies at the core of ongoing debates about the role of RL in
LLM post-training. On one side, strong empirical results can be achieved with
RL even without preceding supervised finetuning; on the other, critics argue
that RL contributes little beyond reweighting existing reasoning strategies.
This work provides concrete evidence that LLMs can acquire genuinely new skills
during RL by composing existing ones, mirroring one of the central mechanisms
by which humans acquire new cognitive skills. To mitigate data contamination
and other confounding factors, and to allow precise control over task
complexity, we develop a synthetic framework for our investigation.
Specifically, we define a skill as the ability to infer the output of a string
transformation function f(x) given x. When an LLM has already learned f and g
prior to RL, our experiments reveal that RL enables it to learn unseen
compositions of them h(x)=g(f(x)). Further, this compositional ability
generalizes to more difficult problems such as compositions of >2 functions
unseen during RL training. Surprisingly, our experiments show that
compositional skill acquired on a source task transfers to a different target
task. This transfer happens even without compositional training on the target,
requiring only prior knowledge of the target’s atomic skills. Our qualitative
analysis shows that RL fundamentally changes the reasoning behaviors of the
models. In contrast, next-token training with the same data yields none of
these findings. Our systematic experiments provide fresh insights into LLM
learning, suggesting the value of first building base models with basic skills,
then using RL to incentivize advanced, generalizable skills for complex
problems.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleAnthropic Plans India Expansion, To Hire Country Lead Amid Global Push
Next Article AMD Expands AI Partnership With Cohere to Power Enterprise and Sovereign AI
Advanced AI Editor
  • Website

Related Posts

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training – Takara TLDR

October 1, 2025

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models – Takara TLDR

October 1, 2025

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech – Takara TLDR

October 1, 2025

Comments are closed.

Latest Posts

Smithsonian Museums to Remain Open Amid Government Shutdown

Statue Left Behind by Grave Robbers Unearthed in Saqqara, Egypt

Security Guards Accuse de Young Museum of Abusive Workplace Culture

Vancouver Art Gallery Taps Canadian Firms to Co-Design New Building

Latest Posts

Client Pressure and the Widening AI Adoption Gap – Artificial Lawyer

October 1, 2025

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training – Takara TLDR

October 1, 2025

OpenAI launches Sora 2 with TikTok-style app

October 1, 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

  • Client Pressure and the Widening AI Adoption Gap – Artificial Lawyer
  • Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training – Takara TLDR
  • OpenAI launches Sora 2 with TikTok-style app
  • MIT Cognitive Scientists Reveal Why Some Sentences Stand Out From Others
  • Character.AI in the spotlight with Karandeep Anand at Disrupt 2025

Recent Comments

  1. binance on Qwen 2.5 Coder and Qwen 3 Lead in Open Source LLM Over DeepSeek and Meta
  2. formula on Stanford HAI’s annual report highlights rapid adoption and growing accessibility of powerful AI systems
  3. formula on Kevin Durant Pulled from Game Due to Health & Safety Protocols
  4. formula on Stanford HAI’s annual report highlights rapid adoption and growing accessibility of powerful AI systems
  5. Williamcum on Foundation AI: Cisco launches AI model for integration in security applications

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.