将强化学习与环境合成结合，为扩展工具使用智能体提供稳健新方法。
arXiv:2605.18703v1 Announce Type: cross Abstract: Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlen…
基于案例的CAST框架，利用历史执行轨迹校准LLM工具使用的推理深度与结构有效性，突破参数知识局限。
arXiv:2605.15041v1 Announce Type: new Abstract: Tool use extends large language models beyond parametric knowledge, but reliable execution requires ba…
论文揭示LLM工具使用中的「知行差距」：模型知道该用工具但实际不用的微妙现象。
arXiv:2605.14038v1 Announce Type: new Abstract: Large language models (LLMs) increasingly act as autonomous agents that must decide when to answer dir…
用方程锚定工具使用，让多模态大模型实现相机鲁棒的3D定位，突破视觉视角限制。
arXiv:2605.19528v1 Announce Type: new Abstract: 3D localization in Multimodal Large Language Models (MLLMs), including 3D object detection and 3D visu…
OpenAI详解Codex App Server构建过程，双向JSON-RPC支持流式进度、工具调用与审批。
Learn how to embed the Codex agent using the Codex App Server, a bidirectional JSON-RPC API powering streaming progress, tool use, approvals, and diff…