SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation

TL;DR

SDialog is an open-source Python toolkit that unifies dialog generation, evaluation, and interpretability for building and analyzing conversational agents with LLMs.

Contribution

It introduces a comprehensive framework combining multi-agent simulation, evaluation metrics, interpretability tools, and audio simulation in a unified dialog-centric architecture.

Findings

Supports persona-driven multi-agent simulation for controlled dialog generation.

Provides diverse evaluation metrics including linguistic and functional correctness.

Includes interpretability tools for activation inspection and steering.

Abstract

We present SDialog, an MIT-licensed open-source Python toolkit that unifies dialog generation, evaluation and mechanistic interpretability into a single end-to-end framework for building and analyzing LLM-based conversational agents. Built around a standardized Dialog representation, SDialog provides: (1) persona-driven multi-agent simulation with composable orchestration for controlled, synthetic dialog generation, (2) comprehensive evaluation combining linguistic metrics, LLM-as-a-judge and functional correctness validators, (3) mechanistic interpretability tools for activation inspection and steering via feature ablation and induction, and (4) audio generation with full acoustic simulation including 3D room modeling and microphone effects. The toolkit integrates with all major LLM backends, enabling mixed-backend experiments under a unified API. By coupling generation, evaluation, and interpretability in a dialog-centric architecture, SDialog enables researchers to build, benchmark and understand conversational systems more systematically.