mlsanityData to 14 Oct 2026

Dialogue Systems Engineering: A Survey and Future Directions

arXiv 2508.02279 ↗First posted 4 Aug 2025cs.SE cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper proposes to refer to the field of software engineering related to the life cycle of dialogue systems as Dialogue Systems Engineering, and surveys this field while also discussing its future directions. With the advancement of large language models, the core technologies underlying dialogue systems have significantly progressed. As a result, dialogue system technology is now expected to be applied to solving various societal issues and in business contexts. To achieve this, it is important to build, operate, and continuously improve dialogue systems correctly and efficiently. Accordingly, in addition to applying existing software engineering knowledge, it is becoming increasingly important to evolve software engineering tailored specifically to dialogue systems. In this paper, we enumerate the knowledge areas of dialogue systems engineering based on those of software engineering, as defined in the Software Engineering Body of Knowledge (SWEBOK) Version 4.0, and survey each area. Based on this survey, we identify unexplored topics in each area and discuss the future direction of dialogue systems engineering.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 134 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

32 of 134 references.

References · 32

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  3. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  4. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 365
  5. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  6. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  7. 2015A Neural Conversational Modelcited by 196
  8. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
  9. 2017ParlAI: A Dialog Research Software Platformcited by 139
  10. 2020Unsupervised Evaluation of Interactive Dialog with DialoGPTcited by 139
  11. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  12. 2017Ethical Challenges in Data-Driven Dialogue Systemscited by 86
20 more
  1. 2020Metamorphic Testing: A New Approach for Generating Next Test Casescited by 75
  2. 2021Software Engineering for AI-Based Systems: A Surveycited by 69
  3. 2017Rasa: Open Source Language Understanding and Dialogue Managementcited by 67
  4. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  5. 2019What Makes a Good Conversation? Challenges in Designing Truly Conversational Agentscited by 42
  6. 2023Using In-Context Learning to Improve Dialogue Safetycited by 42
  7. 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
  8. 2020Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluationcited by 19
  9. 2023Leveraging Implicit Feedback from Deployment Data in Dialoguecited by 14
  10. 2023Leveraging Large Language Models for Automated Dialogue Analysiscited by 14
  11. 2019A Survey of DevOps Concepts and Challengescited by 12
  12. 2021LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcingcited by 11
  13. 2021Software-Based Dialogue Systems: Survey, Taxonomy and Challengescited by 11
  14. 2021Platform for Situated Intelligencecited by 9
  15. 2025Conversation Routines: A Prompt Engineering Framework for Task-Oriented Dialog Systemscited by 8
  16. 2022DialCrowd 2.0: A Quality-Focused Dialog System Crowdsourcing Toolkitcited by 6
  17. 2019An Automated Testing Framework for Conversational Agentscited by 3
  18. 2020DLGNet-Task: An End-to-end Neural Network Framework for Modeling Multi-turn Multi-domain Task-Oriented Dialoguecited by 2
  19. 2024Wizard of Oz Experimentation for Language Technology Applications: Challenges and Toolscited by 2
  20. 2017MACA: A Modular Architecture for Conversational Agentscited by 1

Built on by

Not cited yet.