mlsanityData to 14 Oct 2026

PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback

arXiv 2508.15456 ↗First posted 21 Aug 2025cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Programmable task-oriented dialogue (TOD) agents enable language models to follow structured dialogue policies, but their effectiveness hinges on accurate state tracking. We present PyTOD, an agent that generates executable code to track dialogue state and uses policy and execution feedback for efficient error correction. To this end, 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 state tracking performance on the challenging SGD benchmark. Our experiments show that PyTOD surpasses strong baselines in both accuracy and robust user goal estimation as the dialogue progresses, demonstrating the effectiveness of execution-aware state tracking.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 41 references that are in the map. First posted on arXiv 21 Aug 2025.

Builds on

28 of 41 references.

References · 28

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  3. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  4. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 295
  5. 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 95
  6. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  7. 2023Are LLMs All You Need for Task-Oriented Dialogue?cited by 54
  8. 2021Zero-Shot Dialogue State Tracking via Cross-Task Transfercited by 52
  9. 2022Description-Driven Task-Oriented Dialog Modelingcited by 50
  10. 2020STAR: A Schema-Guided Dialog Dataset for Transfer Learningcited by 44
  11. 2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
  12. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
16 more
  1. 2021SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systemscited by 34
  2. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  3. 2020Schema-Guided Dialogue State Tracking Task at DSTC8cited by 32
  4. 2021Amendable Generation for Dialogue State Trackingcited by 21
  5. 2020Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluationcited by 19
  6. 2024SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Trackingcited by 17
  7. 2022AnyTOD: A Programmable Task-Oriented Dialog Systemcited by 10
  8. 2021Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnosticscited by 9
  9. 2022Dialog2API: Task-Oriented Dialogue with API Description and Example Programscited by 9
  10. 2024Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summariescited by 8
  11. 2023Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptationcited by 7
  12. 2024LUCID: LLM-Generated Utterances for Complex and Interesting Dialoguescited by 7
  13. 2023Continual Dialogue State Tracking via Example-Guided Question Answeringcited by 4
  14. 2024Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systemscited by 4
  15. 2023More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Rankingcited by 2
  16. 2023Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turnscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SpokenUS: A Spoken User Simulator for Task-Oriented Dialoguecited by 1