Milton Montiel

miltmont's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 3 days ago

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 4 days ago • 112

upvoted a paper 9 days ago

The information geometry of large language models is shared, learned, and controllable

Paper • 2609.11063 • Published 24 days ago • 6

upvoted 4 papers 10 days ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 13 days ago • 222

OmniEdu: Open Foundation Models for Learning and Teaching

Paper • 2609.23088 • Published 15 days ago • 237

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Paper • 2609.13814 • Published 22 days ago • 225

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Paper • 2609.24984 • Published 13 days ago • 157

upvoted 3 papers 13 days ago

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Paper • 2608.16590 • Published Aug 17 • 153

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 487

Agora: Git as Shared Memory for Collective AutoResearch

Paper • 2609.18094 • Published 18 days ago • 58

upvoted 2 papers 16 days ago

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published 20 days ago • 434

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 17 days ago • 92

upvoted 4 papers 27 days ago

WorldSculpt: Generating Compositional Worlds from Grounded Videos

Paper • 2609.05416 • Published about 1 month ago • 26

Iris: Climbing to the Search Frontier

Paper • 2609.04304 • Published Sep 3 • 73

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

Paper • 2609.02750 • Published Sep 2 • 144

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published Sep 3 • 20

upvoted 2 papers 28 days ago

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 248

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published Sep 1 • 521

upvoted 3 papers about 1 month ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published Aug 31 • 97

Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO

Paper • 2608.27351 • Published Aug 27 • 22

On-Policy Self-Distillation in Diffusion Models

Paper • 2608.24646 • Published Aug 25 • 70