# Deep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring

arXiv: https://arxiv.org/abs/2604.05854 · HTML: https://mlsanity.com/paper/2604.05854/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 7 of 7)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)

## Abstract (arXiv)

We present 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) 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) Two-Tier Constant-Size Memory -- a memory architecture capped at ~5K characters regardless of runtime duration, preventing the unbounded context growth that plagues long-running agents; and (3) 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.