·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Brian Chesky interview: AI agents need their own operating system1h◆Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs1h◆OpenAI’s new agent is a shot at Meta — but can it compete with free?2h◆Photon held a funeral for mobile apps. Now it has $4.5M to help replace them with agents.2h◆Inside our months-long investigation into Kevin O’Leary’s Utah data center debacle2h◆Hearing tech startup Legato launches its AI hearing glasses3h◆Satlyt, founded by a former Google and SpaceX product manager, raises $8M to run AI on satellites4h◆Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions12h◆Consistent Plan-Act for Long-Horizon Agentic Tasks12h◆Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance12h◆Boosting Adversarial Robustness and Generalization with Dictionary Structure12h◆PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents12h◆TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization12h◆COMiT: Learning Structured Visual Tokens through Sequential Communication12h◆On the (In)effectiveness of AMR Augmentation for Large Language Models12h◆cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents12h◆Compress to Remember: Learning Compact Memory via On-Policy Distillation for Long Video Generation12h◆Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations12h◆Mitigating Memorization In Language Models12h◆MoEless: Efficient MoE LLM Serving with Serverless Experts12h◆Brian Chesky interview: AI agents need their own operating system1h◆Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs1h◆OpenAI’s new agent is a shot at Meta — but can it compete with free?2h◆Photon held a funeral for mobile apps. Now it has $4.5M to help replace them with agents.2h◆Inside our months-long investigation into Kevin O’Leary’s Utah data center debacle2h◆Hearing tech startup Legato launches its AI hearing glasses3h◆Satlyt, founded by a former Google and SpaceX product manager, raises $8M to run AI on satellites4h◆Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions12h◆Consistent Plan-Act for Long-Horizon Agentic Tasks12h◆Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance12h◆Boosting Adversarial Robustness and Generalization with Dictionary Structure12h◆PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents12h◆TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization12h◆COMiT: Learning Structured Visual Tokens through Sequential Communication12h◆On the (In)effectiveness of AMR Augmentation for Large Language Models12h◆cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents12h◆Compress to Remember: Learning Compact Memory via On-Policy Distillation for Long Video Generation12h◆Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations12h◆Mitigating Memorization In Language Models12h◆MoEless: Efficient MoE LLM Serving with Serverless Experts12h◆
News/Rufus-Air: An Open LLM Post-Training Recipe
arxiv
PublishedSeptember 29, 2026 at 4:00 AM
—neutral

Rufus-Air: An Open LLM Post-Training Recipe

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

arXiv:2609.29421v2 Announce Type: replace-cross Abstract: Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and

Stay posted· Newsletter

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

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

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivReasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions12harxivConsistent Plan-Act for Long-Horizon Agentic Tasks12harxivPredictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance12harxivBoosting Adversarial Robustness and Generalization with Dictionary Structure12h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

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

Originally published on arxiv ↗
Built by Marouane Gazouzi
HomeModelsNews