The Agentic Observer Hackathon: Autonomous Decision-making in Simulated Astronomical Surveys
Abstract
Astronomical surveys must allocate observing time while responding to changing conditions and competing scientific priorities. We present the Agentic Observer Hackathon (AOH), a community challenge for studying autonomous survey operations. Within a synthetic multi-object survey with prescribed exposure responses and assignment constraints, decision systems select pointings, assign targets and choose exposure configurations while responding to observing requests, instrumental faults and data loss. We evaluate systems submitted by 102 teams on campaigns reserved for evaluation and analyse target completion in a reference campaign. The leading systems combine numerical exposure planning with language models for interpreting operational information and supporting longer-term decisions. Exploratory tests show improved fault reporting with model access in several systems, while revised scientific priorities produce substantial changes in ranking. The reference campaign traces target completion and diagnoses errors in the baseline's inference of prescribed quality bands. The released simulator and reference strategies provide common survey conditions for comparing exposure allocation, target selection and recovery from interruptions.
Related
- Executable verification through formalized expert reasoning in astronomical spectroscopy
- The Astronomical Hub: A Unified Ecosystem for Modern Astronomical Research
- radio-astro-tools: linking radio astronomical data to the astronomical Python ecosystem
- Automated, auditable dating of the Babylonian Astronomical Diaries with language models and astronomical tools
- Fast Astronomical Transients in Archival Photographic Plates: Using optical aberrations as a tool for discerning real images, from plate artifacts
BibTeX
@misc{wang2026agentic,
title = {{The Agentic Observer Hackathon: Autonomous Decision-making in Simulated Astronomical Surveys}},
author = {Haosong Wang and Ting Tan and Yao Li and Huanyuan Shan and Dezi Liu and Xiangkun Liu and Yifei Luo and Wei Wang and Zonghuan Wu and Zhongxu Zhai},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01988},
eprint = {2611.01988},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01988},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - The Agentic Observer Hackathon: Autonomous Decision-making in Simulated Astronomical Surveys
AU - Haosong Wang
AU - Ting Tan
AU - Yao Li
AU - Huanyuan Shan
AU - Dezi Liu
AU - Xiangkun Liu
AU - Yifei Luo
AU - Wei Wang
AU - Zonghuan Wu
AU - Zhongxu Zhai
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01988
UR - https://arxiv.org/abs/2611.01988
AB - Astronomical surveys must allocate observing time while responding to changing conditions and competing scientific priorities. We present the Agentic Observer Hackathon (AOH), a community challenge for studying autonomous survey operations. Within a synthetic multi-object survey with prescribed exposure responses and assignment constraints, decision systems select pointings, assign targets and choose exposure configurations while responding to observing requests, instrumental faults and data loss. We evaluate systems submitted by 102 teams on campaigns reserved for evaluation and analyse target completion in a reference campaign. The leading systems combine numerical exposure planning with language models for interpreting operational information and supporting longer-term decisions. Exploratory tests show improved fault reporting with model access in several systems, while revised scientific priorities produce substantial changes in ranking. The reference campaign traces target completion and diagnoses errors in the baseline's inference of prescribed quality bands. The released simulator and reference strategies provide common survey conditions for comparing exposure allocation, target selection and recovery from interruptions.
ER -