arXiv
How assigned AI use before class shapes active student engagement in class
AI learning tools are rapidly entering classrooms, but evidence about whether they help students learn is mixed and r...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents
Deployments of research agents are moving to populations of thousands that share one pool of compute, while most curr...
arXiv
Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
How can we predict which base checkpoint is worth an expensive round of agentic post-training? End-to-end pass@$K$ te...
arXiv
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or...
arXiv
Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models
Many of the questions now put to large language models have no correct answer to score against: what a policy is wort...
arXiv
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventi...
arXiv
SciExam for ENSO: Can AI Agents Build Climate Models?
Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usual...
arXiv
RoboJEPA: Scaling Robotic Latent World Models
Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practi...
arXiv
Long-WAM: Scaling the Context of World-Action Models
Real-time robot control demands enough visual history to infer motion and task progress, but processing that history ...
arXiv
Decoupling Exploration from Optimization in RLVR
Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkp...
arXiv
Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos
As we move through the world and carry out everyday tasks, we encounter objects that may become relevant only later. ...
HuggingFace
RunningTab: Direct Workspace Interaction with Environment-Side Tabs
Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to t...