@inproceedings{dong-etal-2026-tartanmaroon,
    title = "{T}artan{M}aroon: Multi-Agent Academic Advising with Iterative Negotiation and Transparent Collaboration",
    author = "Dong, Peidi  and
      Bouamor, Houda  and
      Xiao, Yunze  and
      Kurup, Devi G",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.83/",
    pages = "840--850",
    ISBN = "979-8-89176-392-0",
    abstract = "We present TartanMaroon, a deployable multi-agent academic advising system that handles the full complexity spectrum of student queries, from factual lookups to constrained multi-semester planning. We make three contributions: (1) a proposal{--}critique negotiation protocol in which a Planning Agent generates degree plans evaluated in parallel by domain-specialized agents, enabling detection of cross-domain constraint violations that single-pass outputs miss; (2) a real-time transparency interface streaming agent reasoning and negotiation rounds to users, supported by pilot feedback showing increased trust over standard LLM chatbots; and (3) \textit{TartanBench}, a difficulty-stratified benchmark of 220 advising queries across five complexity tiers, released open-source without exposing individual student records. A five-configuration ablation study establishes a \textit{complexity{--}necessity curve}: single-agent systems perform competitively on simple queries, while multi-agent coordination yields gains of up to $+31$ points on planning tasks."
}