We present \textbf{Deep Researcher Agent}, an open-source framework that enables large language model (LLM) agents to autonomously conduct deep learning experiments around the clock. Unlike existing AI research assistants that focus on paper writing or code generation, our system addresses the full experiment lifecycle: hypothesis formation, code implementation, training execution, result analysis, and iterative refinement. The framework introduces three key innovations: (1) \textbf{Zero-Cost Monitoring} -- a monitoring paradigm that incurs zero LLM API costs during model training by relying solely on process-level checks and log file reads; (2) \textbf{Two-Tier Constant-Size Memory} -- a memory architecture capped at $\sim$5K characters regardless of runtime duration, preventing the unbounded context growth that plagues long-running agents; and (3) \textbf{Minimal-Toolset Leader-Worker Architecture} -- a multi-agent design where each worker agent is equipped with only 3--5 tools, reducing per-call token overhead by up to 73\%. In sustained deployments spanning 30+ days, the framework autonomously completed 500+ experiment cycles across four concurrent research projects, achieving a 52\% improvement over baseline metrics in one project through 200+ automated experiments -- all at an average LLM cost of \$0.08 per 24-hour cycle. Code is available at https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7.

翻译：我们提出 **Deep Researcher Agent**，这是一个开源框架，能让大语言模型（LLM）智能体全天候自主进行深度学习实验。与现有专注于论文撰写或代码生成的AI研究助手不同，我们的系统覆盖完整的实验生命周期：假设形成、代码实现、训练执行、结果分析与迭代优化。该框架引入三项关键创新：（1）**零成本监控**——一种仅依赖进程级检查与日志文件读取、在模型训练期间不产生任何LLM API调用成本的监控范式；（2）**双层恒定容量记忆**——无论运行时多长，记忆架构均限制在约5000字符，防止了长期运行智能体常遭遇的上下文无界增长问题；（3）**最小工具集领导-工作者架构**——一种多智能体设计，每个工作者智能体仅配备3-5个工具，将单次调用的Token开销降低高达73%。在持续30天以上的部署中，该框架在四个并行研究项目中自主完成了500多个实验周期，通过200多次自动化实验使某个项目的基线指标提升了52%——而每个24小时周期的平均LLM成本仅为0.08美元。代码已开源：https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7