METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, a…
In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their aut…
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with…
Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain…
Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We s…
AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pur…
A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns dur…
Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reaso…
LLM developers post-train their models to exhibit prosocial values and behavioral traits, which are enumerated in an ali…
Safety benchmarks typically report one overall score for a suite of datasets, each of which may target one or more safet…
World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control stre…
为什么值得关注：提供了新的研究结果
Self-supervised multimodal representation learning has achieved remarkable success across diverse domains, yet capturing…
为什么值得关注：属于技术进展，可能扩散到其他领域
Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams.Recent metho…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations,…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Agents are deployed in applications from trip planners and stock trading to IT incident triage.In most cases, LLM agents…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Intelligent grading and automated scoring technologies constitute critical infrastructure for smart education.However, e…
为什么值得关注：涉及教育实践，可对照自己的研究场景
Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated…
为什么值得关注：属于技术进展，可能扩散到其他领域
When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or per…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly pro…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响