热点
"工具使用能力" 相关文章
MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use
cs.AI updates on arXiv.org 2025-10-14T04:22:04.000000Z
TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
cs.AI updates on arXiv.org 2025-10-07T04:09:25.000000Z
COLT: Enhancing Video Large Language Models with Continual Tool Usage
cs.AI updates on arXiv.org 2025-09-25T06:13:31.000000Z
10分钟完成 ERNIE-4.5-21B-A3B-Thinking深度思考模型部署
掘金 人工智能 2025-09-13T01:36:32.000000Z
ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools
cs.AI updates on arXiv.org 2025-08-06T04:01:58.000000Z