Autonomous Research Project Management as an Agent Skill: A Case Study in Exact Spectral Spatial Regression

Alexander Chen; Jeffrey Meng; Bram Hoex; Tong Xie

cs.LGSep 16, 2026

Autonomous Research Project Management as an Agent Skill: A Case Study in Exact Spectral Spatial Regression

Authors: Alexander Chen, Jeffrey Meng, Bram Hoex, Tong Xie

Organizations: University of New South Wales · School of Photovoltaic and Renewable Energy Engineering University of New South Wales Kensington, NSW, Australia · GreenDynamics · GreenDynamics Kensington, NSW, Australia

Abstract

This work presents an end-to-end demonstration of autonomous machine learning research conducted by an agent skill on consumer hardware. The demonstration evaluates an FFT-based Kernel Ridge Regression (KRR) solver for regular spatial grids using 2005 monthly NOAA Kaplan SST v2 anomaly fields on a $36 \times 72$ grid. This was autonomously executed by DeepSeek V4 Flash, orchestrated by our agent skill suite within DeepSeek Harness (DSH). Experiments were executed on CPU-only hardware (Apple M2 Pro; 78.7 s solver time, 1.57 GB peak RSS). Long-horizon state was decoupled into a file-based epic- and issue-tracking substrate. Across 74 sub-agent sessions, the agent demonstrated closed-loop scientific resilience: routing two failed hypothesis review gates back to literature retrieval, patching bootstrap indexing bugs, and executing with only four discrete human steering events. Finally, we reflect on autonomous research governance, arguing that scientific credibility requires inspectable state, falsifiable review gates, and transparent reporting of negative results, urging the machine learning community to favour agent-accessible structured formats over static PDF manuscripts.

Figures & tables

Figure 1: 2016-01 test-window field: observed anomalies (missing cells in white) vs. Matérn-3/2 torus reconstruction ( $\lambda{=}10^{-4}$ , Section 1.5.2 ).

Table 2

Panel of Figure 2 — Figure 2: Temporal performance: (a) Nino3.4 index vs. spectral box-functional fit ( $\lambda{=}10^{-2}$ ; CV RMSE 0.0856, corr 0.997); (b) T3 transfer skill vs. climatology by start month and lead ( $n{=}7$ per origin).

Autonomous Research Agents

Autonomous research agents use language models and tools to search literature, design and run experiments, analyze results, and support scientific discovery.

See all 326 papers

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond
Aug 14, 2026Mingming Zhao, Jiqian Dong, Kangping Xu +16Long-Horizon LLM Agents Autonomous Research Agents
Noah’s Ark Lab, Huawei
YouRA: A Persistent-State Architecture for Evidence-Traceable Autonomous Research Agents
Oct 1, 2026Yoonkyu Woo, Woojin Lee, Jin-Xia HuangAI Agent Reliability AI Agents for Scientific Discovery
Electronics and Telecommunications Research Institute, Republic of Korea · Department of Artificial Intelligence, University of Science and Technology, Republic of Korea
Deep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring
Apr 7, 2026Xiangyue ZhangAutonomous Research Agents Autonomous Experimentation
The University of Tokyo

Aug 14, 2026J/K move · Enter open · S save

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond

Mingming Zhao, Jiqian Dong, Kangping Xu, Zadid Hasan+15

Noah’s Ark Lab, Huawei

Long-Horizon LLM Agents Autonomous Research Agents Autonomous Scientific Discovery LLM Agent Workflow Optimization

Open paper AskPDF arXiv

Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources. Pioneering autoresearch agents, despite great success, still lack mechanisms for continuity, recovery from dead ends, and value-driven compute allocation, which inherently undermines overall search efficiency, wastes computational resources, and lowers the chance of ultimate success. To bridge this gap, we introduce ScienceFlow, an end-to-end autoresearch agent framework that organizes long-horizon research work into research segments grounded in executable workspaces. It represents research progress as recoverable executable states, enabling efficient exploration, revision, and execution. Transitions between research segments are governed by Executable-State Transition through Re-Anchoring (ESTRA), which selects either the live state or an archived state as the next anchor and determines whether to continue or redirect the research trajectory. An evidence-aware execution controller allocates resources to physical jobs based on resource availability, remaining budget, and validated progress. We evaluate ScienceFlow on tasks spanning machine learning, scientific modeling, and mathematical optimization. Results on diverse long-horizon benchmarks demonstrate its ability to sustain effective research processes, highlighted by a SOTA 70.22 percent Any-Medal score on the full MLE-bench within a 24-hour budget, outperforming prior reported results by 4.92 percentage points. The efficacy of ScienceFlow further demonstrates that efficient state management, adaptive exploration, and objective-aligned execution are critical for scaling autonomous research beyond short-horizon interactions.

Abstract

Autonomous Research Agents

Explore similar work

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond

YouRA: A Persistent-State Architecture for Evidence-Traceable Autonomous Research Agents

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