SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
| Type of publication: | Conference paper |
| Citation: | Burdisso_EACL_2026 |
| Publication status: | Published |
| Booktitle: | EACL |
| Year: | 2026 |
| 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. |
| Additional Research Programs: |
AI for Everyone |
| Keywords: | |
| Projects: |
ELOQUENCE |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
