CONF Burdisso_EACL_2026/IDIAP SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation Burdisso, Sergio Baroudi, Severin Labrak, Yanis Grunert, David Cyrta, Pawel Chen, Yiyang Madikeri, Srikanth Villatoro-Tello, Esaú Marxer, Ricard Motlicek, Petr EXTERNAL http://publications.idiap.ch/attachments/papers/2026/Burdisso_EACL_2026.pdf PUBLIC EACL 2026 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.