PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback

ACL ARR 2025 February Submission4276 Authors

Abstract: Programmable task-oriented dialogue (TOD) agents enable language models to follow structured dialogue policies, but their effectiveness hinges on accurate state tracking (DST). We present PyTOD, an agent that generates executable code to track dialogue state and uses policy and execution feedback for efficient error correction. To achieve this, PyTOD employs a simple constrained decoding approach, using a language model instead of grammar rules to follow API schemata. This leads to state-of-the-art DST performance on the challenging SGD benchmark. Our experiments show that PyTOD surpasses strong baselines in both accuracy and stability, demonstrating the effectiveness of execution-aware state tracking.

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: task-oriented,grounded dialog,dialogue state tracking,conversational modeling

Contribution Types: NLP engineering experiment, Reproduction study, Publicly available software and/or pre-trained models, Data resources, Data analysis

Languages Studied: English

Submission Number: 4276