…Authors: , , , , , , , , , , , , Abstract PhysicianBench evaluates LLM agents on real clinical tasks requiring complex, multi-step workflows within electronic health record environments, revealing significant gaps in current agent capabilities. AI-generated summary We introduce…
…organized by seven capability dimensions, ten industry categories, and panel-derived difficulty tiers, with item-aligned English, Russian, and Vietnamese renderings. Our construction pipeline rejects 70.3% of LLM -generated candidates at…
…Experimental results demonstrate that Skills-Coach achieves significant performance improvements in skill capability across a wide range of categories, highlighting its potential to advance the development of more robust and adaptable LLM…
…Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments Published on Apr 28 Submitted by Amir on Apr 30 Authors: Amir Saeidi , , , , , , Abstract Failure-Aware Meta-Agentic…
…LLMs by scaling test-time compute. However, existing approaches typically require either training recurrent models from scratch or applying disruptive retrofits, which involve substantial computational costs and may compromise pretrained capabilities. To…
…Cheng Qian , , Jiayu Liu , , , , , , , , , , Abstract Large language models demonstrate limited creative problem-solving abilities when required to repurpose objects based on affordance reasoning, indicating a gap in current AI capabilities for novel…
…Conversely, while Large Language Models (LLMs) demonstrate impressive reasoning capabilities, they lack the capacity to predict future geometric evolution, creating a significant disparity between semantic interpretation and physical simulation. To bridge this…
…AI-generated summary As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the inference efficiency of long-context…
…Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents Published on May 13 Submitted by Mikhail Menschikov on May 14 Skoltech Authors: Mikhail Menschikov , , , , , , , , , , Abstract PersonalAI 2.0 enhances…
…icu lt to assess the true reasoning capabilities of AI systems. We introduce Real ICU , a hindsight-annotated benchmark for evaluating large language models (LLMs) under realistic ICU conditions, where labels are…