@inproceedings{jia-etal-2026-spec,
    title = "Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection",
    author = "Jia, Minghui  and
      Zhang, Qichao  and
      Luo, Ali  and
      Li, Linjing  and
      Ye, Shuo  and
      Lu, Hailing  and
      Hou, Wen  and
      Zhao, Dongbin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.256/",
    pages = "5662--5681",
    ISBN = "979-8-89176-390-6",
    abstract = "Due to the limited generalization and interpretability of deep learning classifiers, the final vetting of rare celestial object candidates still relies on manually intensive expert visual inspection, which has become a primary bottleneck as modern spectroscopic surveys continue to scale.To bridge this gap, we propose Spec-o3, a tool-augmented vision-language agent that performs astronomer-aligned spectral inspection via interleaved multimodal chain-of-thought reasoning.Spec-o3 is trained with a two-stage post-training recipe: cold-start supervised fine-tuning on expert inspection trajectories followed by outcome-based reinforcement learning on rare-type verification tasks.Evaluated on five rare-object identification tasks from LAMOST, Spec-o3 establishes a new State-of-the-Art, boosting the macro-F1 score from 28.3 to 76.5 with a 7B parameter base model and outperforming both proprietary VLMs and specialized deep models. Beyond accuracy, Spec-o3 processes spectra at $\sim$0.2 s per sample on an 8$\times$H100 server, a $\sim$50$\times$ throughput gain over expert manual inspection. The agent also demonstrates strong generalization to unseen inspection tasks across survey shifts (from LAMOST to SDSS/DESI). Expert evaluations further confirm that its reasoning traces are coherent and physically consistent, supporting transparent and trustworthy decision-making.Code, data, and models are available at Project HomePage."
}