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

How DeepSeek AI will reshape Nigeria’s business landscape

OpenAI and Anthropic evaluated each others’ models – which ones came out on top

Data Reveals AI Search Dominance Is False Narrative, So Far 08/28/2025

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

rStar2-Agent: Agentic Reasoning Technical Report – Takara TLDR

By Advanced AI EditorAugust 30, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


We introduce rStar2-Agent, a 14B math reasoning model trained with agentic
reinforcement learning to achieve frontier-level performance. Beyond current
long CoT, the model demonstrates advanced cognitive behaviors, such as thinking
carefully before using Python coding tools and reflecting on code execution
feedback to autonomously explore, verify, and refine intermediate steps in
complex problem-solving. This capability is enabled through three key
innovations that makes agentic RL effective at scale: (i) an efficient RL
infrastructure with a reliable Python code environment that supports
high-throughput execution and mitigates the high rollout costs, enabling
training on limited GPU resources (64 MI300X GPUs); (ii) GRPO-RoC, an agentic
RL algorithm with a Resample-on-Correct rollout strategy that addresses the
inherent environment noises from coding tools, allowing the model to reason
more effectively in a code environment; (iii) An efficient agent training
recipe that starts with non-reasoning SFT and progresses through multi-RL
stages, yielding advanced cognitive abilities with minimal compute cost. To
this end, rStar2-Agent boosts a pre-trained 14B model to state of the art in
only 510 RL steps within one week, achieving average pass@1 scores of 80.6% on
AIME24 and 69.8% on AIME25, surpassing DeepSeek-R1 (671B) with significantly
shorter responses. Beyond mathematics, rStar2-Agent-14B also demonstrates
strong generalization to alignment, scientific reasoning, and agentic tool-use
tasks. Code and training recipes are available at
https://github.com/microsoft/rStar.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleHow OpenAI is reworking ChatGPT after landmark wrongful death lawsuit
Next Article Tesla to make app change for easier communication following Service
Advanced AI Editor
  • Website

Related Posts

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning – Takara TLDR

August 30, 2025

Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection – Takara TLDR

August 30, 2025

OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning – Takara TLDR

August 30, 2025

Comments are closed.

Latest Posts

Woodmere Art Museum Sues Trump Administration Over Canceled IMLS Grant

Barbara Gladstone’s Chelsea Townhouse in NYC Sells for $13.1 M.

Trump Meets with Smithsonian Leader Amid Threats of Content Review

Australian School Faces Pushback over AI Art Course—and More Art News

Latest Posts

How DeepSeek AI will reshape Nigeria’s business landscape

August 31, 2025

OpenAI and Anthropic evaluated each others’ models – which ones came out on top

August 31, 2025

Data Reveals AI Search Dominance Is False Narrative, So Far 08/28/2025

August 31, 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

  • How DeepSeek AI will reshape Nigeria’s business landscape
  • OpenAI and Anthropic evaluated each others’ models – which ones came out on top
  • Data Reveals AI Search Dominance Is False Narrative, So Far 08/28/2025
  • Nvidia says two mystery customers accounted for 39% of Q2 revenue
  • Elon Musk’s xAI Hits Ex-Employee With Lawsuit Claiming Trade Secrets Ended Up At OpenAI

Recent Comments

  1. JosephHar on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  2. MashaOi9497 on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. JosephHar on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  4. リアル ラブドール on A New Trick Could Block the Misuse of Open Source AI
  5. kitchen Towels 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.