@inproceedings{burdisso-etal-2026-sdialog,
    title = "{SD}ialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation",
    author = {Burdisso, Sergio  and
      Baroudi, S{\'e}verin  and
      Labrak, Yanis  and
      Gr{\"u}nert, David  and
      Cyrta, Pawel  and
      Chen, Yiyang  and
      Madikeri, Srikanth  and
      Villatoro-tello, Esa{\'u}  and
      Marxer, Ricard  and
      Motlicek, Petr},
    editor = "Croce, Danilo  and
      Leidner, Jochen  and
      Moosavi, Nafise Sadat",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = mar,
    year = "2026",
    address = "Rabat, Marocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-demo.23/",
    pages = "320--340",
    ISBN = "979-8-89176-382-1",
    abstract = "We present SDialog, an MIT-licensed open-source Python toolkit for end-to-end development, simulation, evaluation, and analysis of LLM-based conversational agents. Built around a standardized Dialog representation, SDialog unifies persona-driven multi-agent simulation with composable orchestration for controlled synthetic dialog generation; multi-layer evaluation combining linguistic metrics, LLM-as-a-judge assessments, and functional correctness validators; mechanistic interpretability tools for activation inspection and causal behavior steering via feature ablation and induction; and audio rendering with full acoustic simulation, including 3D room modeling and microphone effects. The toolkit integrates with major LLM backends under a consistent API, enabling mixed-backend and reproducible experiments. By bridging agent construction, user simulation, dialog generation, evaluation, and interpretability within a single coherent workflow, SDialog enables more controlled, transparent, and systematic research on conversational systems."
}