Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents
Research
Research News
New papers, breakthroughs and academic AI research
OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
Research
OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation
Research
CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models
Research
NeuroAI and Beyond: Bridging Between Advances in Neuroscience and Artificial Intelligence
Research
Safety of Latent Communication in Multi-Agent Systems
Research
Ranking-Aware Prompt Optimization for Multimodal Clinical Diagnosis
Research
Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training
Research
CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidance
Research
Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
Research
FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy
Research
Bimanual Robot Manipulation via Multi-Agent In-Context Learning
Research