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

Microsoft Layoffs Continue | Recruiting News Network

Harmony Version Doubao Empowers, Multi-Modal Large Model Experience Evolves_voice_user_and

DeepSeek-R1 and Tencent Hunyuan Empower Content Platforms_the_user_models

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

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward – Takara TLDR

By Advanced AI EditorSeptember 12, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


A central paradox in fine-tuning Large Language Models (LLMs) with
Reinforcement Learning with Verifiable Reward (RLVR) is the frequent
degradation of multi-attempt performance (Pass@k) despite improvements in
single-attempt accuracy (Pass@1). This is often accompanied by catastrophic
forgetting, where models lose previously acquired skills. While various methods
have been proposed, the choice and function of the divergence term have been
surprisingly unexamined as a proactive solution. We argue that standard RLVR
objectives — both those using the mode-seeking reverse KL-divergence and those
forgoing a divergence term entirely — lack a crucial mechanism for knowledge
retention. The reverse-KL actively accelerates this decay by narrowing the
policy, while its absence provides no safeguard against the model drifting from
its diverse knowledge base. We propose a fundamental shift in perspective:
using the divergence term itself as the solution. Our framework,
Diversity-Preserving Hybrid RL (DPH-RL), leverages mass-covering f-divergences
(like forward-KL and JS-divergence) to function as a rehearsal mechanism. By
continuously referencing the initial policy, this approach forces the model to
maintain broad solution coverage. Extensive experiments on math and SQL
generation demonstrate that DPH-RL not only resolves the Pass@k degradation but
improves both Pass@1 and Pass@k in- and out-of-domain. Additionally, DPH-RL is
more training-efficient because it computes f-divergence using generator
functions, requiring only sampling from the initial policy and no online
reference model. Our work highlights a crucial, overlooked axis for improving
RLVR, demonstrating that the proper selection of a divergence measure is a
powerful tool for building more general and diverse reasoning models.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleBulgarian Doctoral Student Anna-Maria Halacheva Recognized by European Commission – Novinite.com
Next Article Australia’s biggest bank cut staff for AI, then it backtracked – and it’s one of many scrapping plans for automated customer support teams
Advanced AI Editor
  • Website

Related Posts

Research Paper – Takara TLDR

September 12, 2025

2D Gaussian Splatting with Semantic Alignment for Image Inpainting – Takara TLDR

September 12, 2025

OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning – Takara TLDR

September 12, 2025

Comments are closed.

Latest Posts

Long-Lost Painting By Rubens From 1613 Discovered in Paris Mansion

Ken Griffin Loves Pollock’s Blue Poles So Much He Tried to Buy it

Nan Goldin Says Her Market ‘Tanked’ Due to Palestine Activism

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

Latest Posts

Microsoft Layoffs Continue | Recruiting News Network

September 12, 2025

Harmony Version Doubao Empowers, Multi-Modal Large Model Experience Evolves_voice_user_and

September 12, 2025

DeepSeek-R1 and Tencent Hunyuan Empower Content Platforms_the_user_models

September 12, 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

  • Microsoft Layoffs Continue | Recruiting News Network
  • Harmony Version Doubao Empowers, Multi-Modal Large Model Experience Evolves_voice_user_and
  • DeepSeek-R1 and Tencent Hunyuan Empower Content Platforms_the_user_models
  • SlatorCon Recap, Cohere’s Big AI Translation Launch, TransPerfect Buys Unbabel
  • Tosda Launches Embodied Intelligent Robot Empowered by Zhipu AI, Enabling Flexible Production **AI Robot**_robot_the_This

Recent Comments

  1. WalterSkete on Implement human-in-the-loop confirmation with Amazon Bedrock Agents
  2. Jasonsof on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. WalterSkete on This AI Hallucinates Images For You
  4. Jasonsof on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  5. RodneyKek 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.