John Giles III

maxnumbers's activity

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

upvoted 2 papers about 15 hours ago

Scaling Mathematical Proof Supervision from Structured Textbooks

Paper • 2610.40394 • Published 17 days ago • 48

Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

Paper • 2611.17167 • Published 3 days ago • 32

upvoted a paper 1 day ago

Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

Paper • 2611.14320 • Published 5 days ago • 71

upvoted 2 papers 4 days ago

IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?

Paper • 2611.03424 • Published 13 days ago • 48

Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery

Paper • 2611.12762 • Published 6 days ago • 59

upvoted 3 papers 5 days ago

AutoCompress: Automated Hardware-Guided Model Compression

Paper • 2611.08290 • Published 9 days ago • 13

Exploring Weight-Space Programming: Capabilities, Generalization, and Limitations

Paper • 2611.09382 • Published 9 days ago • 20

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 20 days ago • 116

upvoted a paper 11 days ago

Your Benchmark Is an Empirical Measure Over Difficulty

Paper • 2610.29927 • Published 25 days ago • 27

upvoted 2 papers 15 days ago

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

Paper • 2610.28763 • Published 26 days ago • 19

Cache Engineering for Agents

Paper • 2610.28577 • Published 26 days ago • 105

upvoted a paper 19 days ago

PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean

Paper • 2610.31810 • Published 24 days ago • 9

upvoted a paper 23 days ago

Agentic World Action Models

Paper • 2610.30136 • Published 25 days ago • 12

upvoted 5 papers about 1 month ago

PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs

Paper • 2609.34715 • Published Sep 28 • 27

RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement

Paper • 2609.39045 • Published Sep 30 • 45

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Paper • 2609.33439 • Published Sep 27 • 100

What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

Paper • 2609.34981 • Published Sep 29 • 79

In-Context Learning for Robots: Methods and Applications

Paper • 2609.36012 • Published Sep 28 • 90

upvoted 2 papers about 2 months ago

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

Paper • 2609.11063 • Published Sep 10 • 6

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published Sep 21 • 164