·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Meta removes controversial AI feature on Instagram after backlash3h◆Meta turns off the Instagram feature that let users make AI deepfakes of public accounts3h◆Apple sues OpenAI for allegedly stealing hardware secrets6h◆Apple sues OpenAI over alleged trade secret theft6h◆Open source AI matters more than ever, according to Hugging Face’s Clem Delangue8h◆SK Hynix raises $26.5B in the biggest foreign IPO in US history, is urged to build new US fabs10h◆Hugging Face’s CEO on why companies are done renting their AI13h◆Instagram’s Adam Mosseri: If you don’t like AI, ‘then you shouldn’t have it in your feed’14h◆Would you host part of an AI data center in your home?14h◆How Deutsche Telekom is rewiring telecommunications with AI20h◆Svarna: An Open Corpus Workbench for Modern Greek23h◆When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals23h◆PLURAL: A Global Dataset for Value Alignment23h◆BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression23h◆Infinity-Parser2 Technical Report23h◆Agentic Neural Architecture Search23h◆Leveraging Color Naming for Image Enhancement23h◆($\theta_l, \theta_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces23h◆MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs23h◆Generalization Theory for Through-the-Wall Radar Human Activity Recognition23h◆Meta removes controversial AI feature on Instagram after backlash3h◆Meta turns off the Instagram feature that let users make AI deepfakes of public accounts3h◆Apple sues OpenAI for allegedly stealing hardware secrets6h◆Apple sues OpenAI over alleged trade secret theft6h◆Open source AI matters more than ever, according to Hugging Face’s Clem Delangue8h◆SK Hynix raises $26.5B in the biggest foreign IPO in US history, is urged to build new US fabs10h◆Hugging Face’s CEO on why companies are done renting their AI13h◆Instagram’s Adam Mosseri: If you don’t like AI, ‘then you shouldn’t have it in your feed’14h◆Would you host part of an AI data center in your home?14h◆How Deutsche Telekom is rewiring telecommunications with AI20h◆Svarna: An Open Corpus Workbench for Modern Greek23h◆When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals23h◆PLURAL: A Global Dataset for Value Alignment23h◆BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression23h◆Infinity-Parser2 Technical Report23h◆Agentic Neural Architecture Search23h◆Leveraging Color Naming for Image Enhancement23h◆($\theta_l, \theta_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces23h◆MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs23h◆Generalization Theory for Through-the-Wall Radar Human Activity Recognition23h◆
News/Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
arxiv
PublishedJune 30, 2026 at 4:00 AM

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

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

arXiv:2606.30616v1 Announce Type: new Abstract: We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling het

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
arxivSvarna: An Open Corpus Workbench for Modern Greek23harxivWhen LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals23harxivPLURAL: A Global Dataset for Value Alignment23harxivBiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression23h
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 ↗
HomeModelsNews