·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Nvidia launches new open models to run agents in the enterprise and on PCs33m◆JB Pritzker thinks AI could help us live to 100 — or threaten us like nukes1h◆A hacker broke into John Deere and SharkNinja with an army of AI agents2h◆Democrats think cracking down on AI could give them an edge4h◆AI researchers stranded Claude on a virtual desert island. It started to “play.”7h◆A Theoretical Analysis of Test-Driven Code Generation12h◆Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video12h◆Can Graph Learning Learn Circuits?12h◆Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery12h◆Trajectory-Guided Steering: Mitigating Spurious Feature Bias in Clinical Classification12h◆Sentence-Level Topic Modeling with Lexical and Contextual Evidence12h◆Referring Multi-Object Tracking with Diverse Dynamic Expressions12h◆Rarity of Singletons Matters & Supplementary Materials12h◆TANGO: RNA Topology and Geometry Co-Design12h◆Handwritten Text Recognition Lives in the High-Pixel Variance Subspace12h◆RealtimeWAM: One-Step Asynchronous World Action Models12h◆How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference?12h◆R$^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution12h◆Logic-Guided Graph Denoising Diffusion Models12h◆Unit-level aggregation breaks coverage in causal foundation models12h◆Nvidia launches new open models to run agents in the enterprise and on PCs33m◆JB Pritzker thinks AI could help us live to 100 — or threaten us like nukes1h◆A hacker broke into John Deere and SharkNinja with an army of AI agents2h◆Democrats think cracking down on AI could give them an edge4h◆AI researchers stranded Claude on a virtual desert island. It started to “play.”7h◆A Theoretical Analysis of Test-Driven Code Generation12h◆Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video12h◆Can Graph Learning Learn Circuits?12h◆Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery12h◆Trajectory-Guided Steering: Mitigating Spurious Feature Bias in Clinical Classification12h◆Sentence-Level Topic Modeling with Lexical and Contextual Evidence12h◆Referring Multi-Object Tracking with Diverse Dynamic Expressions12h◆Rarity of Singletons Matters & Supplementary Materials12h◆TANGO: RNA Topology and Geometry Co-Design12h◆Handwritten Text Recognition Lives in the High-Pixel Variance Subspace12h◆RealtimeWAM: One-Step Asynchronous World Action Models12h◆How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference?12h◆R$^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution12h◆Logic-Guided Graph Denoising Diffusion Models12h◆Unit-level aggregation breaks coverage in causal foundation models12h◆
News/NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
arxiv
PublishedOctober 16, 2026 at 4:00 AM

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

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

arXiv:2609.08183v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We present NeoHorse-1, a family of agent-native models developed to expl

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
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivA Theoretical Analysis of Test-Driven Code Generation12harxivScalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video12harxivCan Graph Learning Learn Circuits?12harxivBeyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery12h
The Bubble Brief
MON · WED · FRI

Read AI 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