·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Cursor makes its biggest India push yet ahead of SpaceX acquisition with localized pricing4h◆Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting5h◆Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex5h◆Market Design for AI: Beyond the Copyright Binary5h◆Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents5h◆TextRich: A Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-25h◆DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning5h◆From World Models to World Action Models: A Concise Tutorial for Robotics5h◆QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting5h◆Multi-Turn On-Policy Distillation with Prefix Replay5h◆Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary5h◆Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts5h◆MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents5h◆PhantomFill: When the Form Demands an Answer, Language Models Invent One5h◆Error Certificates for KV-Cache Eviction via Randomized Design5h◆Explaining GAND: A Resource on Gender-Ambiguous Natural Data & Contrastive Attribution5h◆MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilities5h◆LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction5h◆Mwando: Leveraging AI to Preserve and Teach shiKomori5h◆The JEPA Paradox in Language: The Geometry of Linguistic Alternatives5h◆Cursor makes its biggest India push yet ahead of SpaceX acquisition with localized pricing4h◆Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting5h◆Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex5h◆Market Design for AI: Beyond the Copyright Binary5h◆Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents5h◆TextRich: A Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-25h◆DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning5h◆From World Models to World Action Models: A Concise Tutorial for Robotics5h◆QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting5h◆Multi-Turn On-Policy Distillation with Prefix Replay5h◆Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary5h◆Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts5h◆MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents5h◆PhantomFill: When the Form Demands an Answer, Language Models Invent One5h◆Error Certificates for KV-Cache Eviction via Randomized Design5h◆Explaining GAND: A Resource on Gender-Ambiguous Natural Data & Contrastive Attribution5h◆MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilities5h◆LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction5h◆Mwando: Leveraging AI to Preserve and Teach shiKomori5h◆The JEPA Paradox in Language: The Geometry of Linguistic Alternatives5h◆
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

A 5-min weekly brief — top movers, price watch, story of the week.

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

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
arxivReverso: Efficient Time Series Foundation Models for Zero-shot Forecasting5harxivMultinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex5harxivMarket Design for AI: Beyond the Copyright Binary5harxivWho Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents5h
The Bubble Brief
WEEKLY

Read long-context insights every Tuesday — top movers, new releases, story of the week.

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

Originally published on arxiv ↗
HomeModelsNews