·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning9h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks9h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts9h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning9h◆FrontierChallenge: Evaluating Scientific Workflow Completion9h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier9h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising9h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic9h◆Omni Interaction Agent Technical Report9h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification9h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability9h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization9h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding9h◆Tracing Computation Density in LLMs9h◆Cultural Binding Heads in Language Models9h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training9h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models9h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning9h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection9h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation9h◆Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning9h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks9h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts9h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning9h◆FrontierChallenge: Evaluating Scientific Workflow Completion9h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier9h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising9h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic9h◆Omni Interaction Agent Technical Report9h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification9h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability9h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization9h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding9h◆Tracing Computation Density in LLMs9h◆Cultural Binding Heads in Language Models9h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training9h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models9h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning9h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection9h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation9h◆
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
arxivBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning9harxivSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks9harxivDistribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts9harxivIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning9h
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