As agents continuously improve by generating and revising Skills, the process that discovers and refines those Skills be…
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
Multimodal assistants answer questions from long-term memories that contain images.After retrieval, each retrieved image…
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 have become the dominant paradigm for visual understanding, but incur substantial costs…
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
Tabular foundation models (TFMs) achieve strong predictive performance by conditioning on labeled demonstrations provide…
为什么值得关注：属于企业动态，反映产业投入方向
World models are usually judged from the inside: by prediction loss, by the return a policy earns in imagination, or by…
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
AI agents are increasingly being programmed to automate knowledge work over large collections of unstructured data.Such…
为什么值得关注：属于技术进展，可能扩散到其他领域
LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool…
为什么值得关注：属于技术进展，可能扩散到其他领域
Frontier LLM agents have been shown to be capable of solving increasingly complex tasks for which humans have measurable…
为什么值得关注：属于科研论文，可作为研究依据
Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through sca…
为什么值得关注：属于技术进展，可能扩散到其他领域
LLM tool-use agents operate in dynamic environments where many actions carry operational risk.However, most safety mecha…
为什么值得关注：属于技术进展，可能扩散到其他领域
In semantic query engines, predicates are evaluated by machine-learned models, and the choice of a query plan affects no…
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
Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the l…
为什么值得关注：属于技术进展，可能扩散到其他领域
Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advan…
Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicit…
Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirem…
Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineeri…
Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying…
Attacker ASV systems for voice anonymization have been studied primarily in English, leaving their behavior in multiling…
End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic ex…
Product Identification has sprung up to become one of the most challenging problems in the automation of the retail indu…