·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Blue Planet III is keeping the rough edges in the age of AI8h◆The AI graveyard: a running list of projects and startups that didn’t make it10h◆Pennsylvania will require labels on AI-generated ads11h◆Block’s new voice model sounds eerily human13h◆Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.14h◆Here are the top AI agents that can live in your text messages15h◆OpenAI says it will no longer train its AI models on the live internet, citing “significant risks”1d◆Hottest toy for Christmas? Nvidia CEO plays with adorable Microduck robots, 20,000 sell1d◆OpenAI now trains its frontier AI models with no internet access1d◆Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend1d◆From Toast to Bessemer: Who founders will hear from at TechCrunch Founder Summit 20261d◆The iPhone Duo should have been an iPad1d◆Rapidly scaling online storage to serve over 1 billion ChatGPT users (Part II)1d◆Now Google says it might use your Gmail and Google Photos data to target ads1d◆LitPivot: Developing research ideas through dynamic contextualization within the literature landscape1d◆Meta delays new business terms after publisher pushback on AI scraping1d◆Retro gaming is being overrun with AI1d◆Securing our frontier model training environment1d◆VeriEvolve: Evaluator-First Evolution for Tool-Using Agents2d◆TNODEV: Toolbox for Neural ODE Verification2d◆Blue Planet III is keeping the rough edges in the age of AI8h◆The AI graveyard: a running list of projects and startups that didn’t make it10h◆Pennsylvania will require labels on AI-generated ads11h◆Block’s new voice model sounds eerily human13h◆Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.14h◆Here are the top AI agents that can live in your text messages15h◆OpenAI says it will no longer train its AI models on the live internet, citing “significant risks”1d◆Hottest toy for Christmas? Nvidia CEO plays with adorable Microduck robots, 20,000 sell1d◆OpenAI now trains its frontier AI models with no internet access1d◆Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend1d◆From Toast to Bessemer: Who founders will hear from at TechCrunch Founder Summit 20261d◆The iPhone Duo should have been an iPad1d◆Rapidly scaling online storage to serve over 1 billion ChatGPT users (Part II)1d◆Now Google says it might use your Gmail and Google Photos data to target ads1d◆LitPivot: Developing research ideas through dynamic contextualization within the literature landscape1d◆Meta delays new business terms after publisher pushback on AI scraping1d◆Retro gaming is being overrun with AI1d◆Securing our frontier model training environment1d◆VeriEvolve: Evaluator-First Evolution for Tool-Using Agents2d◆TNODEV: Toolbox for Neural ODE Verification2d◆
News/A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation
arxiv
PublishedJune 17, 2026 at 4:00 AM
—neutral

A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.12227v2 Announce Type: replace Abstract: Existing approaches to post-train models for long-context tasks face complementary limitations: (i) supervised fine-tuning (SFT) provides stable supervision but suffers from exposure bias; (ii) reinforcement learning methods such as Group Relative

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Mentioned models
02
  • 01
    Group Relative Policy Optimization (GRPO)
  • 02
    on-policy distillation (OPD)
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#long-context#reinforcement learning#distillation#multilingual

No replies yet. Be first.

Mentioned models
02
  • 01
    Group Relative Policy Optimization (GRPO)
  • 02
    on-policy distillation (OPD)
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#long-context#reinforcement learning#distillation#multilingual

Related coverage

More from ARXIV
arxivVeriEvolve: Evaluator-First Evolution for Tool-Using Agents2darxivTNODEV: Toolbox for Neural ODE Verification2d
The Bubble Brief
MON · WED · FRI

Read long-context insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews