AI论文速递 2026年05月11日（HuggingFace Daily Papers）¶

数据来源：https://huggingface.co/papers 采集时间：2026-05-11

📌 重点关注¶

Audio-Visual Intelligence in Large Foundation Models | arXiv — 【重点关注】 Audio-Visual Intelligence (AVI) has emerged as a central frontier in artifici... 💡 多模态融合的新突破，为AI Agent提供更丰富的感知能力
BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models | arXiv — 【重点关注】 Despite the success of large language models (LLMs) on general-purpose tasks,... 💡 专业领域数据集，为AI Agent在医疗场景提供训练基础
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms | arXiv — 【重点关注】 Large Language Model (LLM)-based agents have fundamentally reshaped artificia... 💡 Agent记忆机制演进综述，为长期记忆设计提供理论指导

CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment | arXiv — Large language models (LLMs) have become a central foundation of modern artif...
EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions | arXiv — Multimodal Large Language Models (MLLMs) hold significant promise for revolut...
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search | arXiv — Existing benchmarks for multimodal agentic search evaluate multimodal search ...
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction | arXiv — Modern retrieval systems, whether lexical or semantic, expose a corpus throug...
A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping | arXiv — Reinforcement learning for agentic large language models (LLMs) typically rel...
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling | arXiv — Test-time scaling (TTS) has become an effective approach for improving large ...
RemoteZero: Geospatial Reasoning with Zero Human Annotations | arXiv — Geospatial reasoning requires models to resolve complex spatial semantics and...