OSWorld-Pro: Process-based Evaluation for Computer Use Agents Paper • 2609.24890 • Published 20 days ago • 28
LEGO-Anything: Coding Agents for 3D Scene Reconstruction Paper • 2609.36380 • Published 13 days ago • 130
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence Paper • 2609.35432 • Published 13 days ago • 109
view article Article Coordinating a real-time voice model with a separate task-execution agent: a practical architecture NatalieY • Sep 10 • 3
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning Paper • 2609.35767 • Published 13 days ago • 50
Jev-style decision models: open data Collection Data for Jev-style decision models. Notes say where labels come from: humans, exact rules or an LLM teacher. Last updated 2026-09-24. • 17 items • Updated 17 days ago • 9
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 376
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published 26 days ago • 560
Agora: Git as Shared Memory for Collective AutoResearch Paper • 2609.18094 • Published 25 days ago • 58
Wearables AI Workshop - ECCV 2026 Collection 🏆 Datasets and models of Winning solutions for the EgoLongQA and EgoProactive - Meta Wearable AI Grand Challenge (ECCV 2026). • 6 items • Updated Sep 8 • 2
Memory as Plans: World-Action Modeling with Memory-Grounded Planning Paper • 2609.11561 • Published Sep 10 • 41
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them? Paper • 2609.10226 • Published Sep 9 • 19
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training Paper • 2609.07108 • Published Sep 7 • 36
uno Collection Unlocking Lossless Speedups in LLMs via Discrete Diffusion • 4 items • Updated Sep 8 • 8
view article Article NeoMME: an efficient Multimodal-native and Multilingual Encoder Hcompany • Sep 3 • 121