Macaron-A2UI: A Model for Generative UI in Personal Agents Paper • 2605.24830 • Published 6 days ago • 77
From Word to World: Can Large Language Models be Implicit Text-based World Models? Paper • 2512.18832 • Published Dec 21, 2025 • 15
Thickening-to-Thinning: Reward Shaping via Human-Inspired Learning Dynamics for LLM Reasoning Paper • 2602.04265 • Published Feb 4
$δ$-mem: Efficient Online Memory for Large Language Models Paper • 2605.12357 • Published 18 days ago • 123
MinT: Managed Infrastructure for Training and Serving Millions of LLMs Paper • 2605.13779 • Published 17 days ago • 218
Macaron-A2UI: A Model for Generative UI in Personal Agents Paper • 2605.24830 • Published 6 days ago • 77
Macaron-A2UI: A Model for Generative UI in Personal Agents Paper • 2605.24830 • Published 6 days ago • 77
InfoPO: Information-Driven Policy Optimization for User-Centric Agents Paper • 2603.00656 • Published Feb 28 • 9
MinT: Managed Infrastructure for Training and Serving Millions of LLMs Paper • 2605.13779 • Published 17 days ago • 218
MinT: Managed Infrastructure for Training and Serving Millions of LLMs Paper • 2605.13779 • Published 17 days ago • 218
MinT: Managed Infrastructure for Training and Serving Millions of LLMs Paper • 2605.13779 • Published 17 days ago • 218
MinT: Managed Infrastructure for Training and Serving Millions of LLMs Paper • 2605.13779 • Published 17 days ago • 218