mlsanityData to 14 Oct 2026

Planning with Diffusion Models for Target-Oriented Dialogue Systems

arXiv 2504.16858 ↗First posted 23 Apr 2025cs.CLcited by 0

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Target-Oriented Dialogue (TOD) remains a significant challenge in the LLM era, where strategic dialogue planning is crucial for directing conversations toward specific targets. However, existing dialogue planning methods generate dialogue plans in a step-by-step sequential manner, and may suffer from compounding errors and myopic actions. To address these limitations, we introduce a novel dialogue planning framework, DiffTOD, which leverages diffusion models to enable non-sequential dialogue planning. DiffTOD formulates dialogue planning as a trajectory generation problem with conditional guidance, and leverages a diffusion language model to estimate the likelihood of the dialogue trajectory. To optimize the dialogue action strategies, DiffTOD introduces three tailored guidance mechanisms for different target types, offering flexible guidance toward diverse TOD targets at test time. Extensive experiments across three diverse TOD settings show that DiffTOD can effectively perform non-myopic lookahead exploration and optimize action strategies over a long horizon through non-sequential dialogue planning, and demonstrates strong flexibility across complex and diverse dialogue scenarios. Our code and data are accessible through https://github.com/ninglab/DiffTOD.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 46 of its 81 references that are in the map. First posted on arXiv 23 Apr 2025.

Builds on

46 of 81 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning18 Oct
  2. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct
  3. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model5 Jun
  4. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models17 Oct

Other references · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  11. 2017Hindsight Experience Replaycited by 1,136
  12. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
30 more
  1. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  2. 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 840
  3. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  4. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 482
  5. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 422
  6. 2023DeepCache: Accelerating Diffusion Models for Freecited by 359
  7. 2023Nearly d-Linear Convergence Bounds for Diffusion Models via Stochastic Localizationcited by 235
  8. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 162
  9. 2023Protein Design with Guided Discrete Diffusioncited by 157
  10. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 116
  11. 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learningcited by 115
  12. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 77
  13. 2019Target-Guided Open-Domain Conversationcited by 66
  14. 2023A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospectscited by 66
  15. 2022Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstrationcited by 54
  16. 2024Towards Human-centered Proactive Conversational Agentscited by 49
  17. 2024Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexitycited by 42
  18. 2023Adaptive Online Replanning with Diffusion Modelscited by 34
  19. 2024Planning Like Human: A Dual-process Framework for Dialogue Planningcited by 32
  20. 2023Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Modelscited by 31
  21. 2023DialogBench: Evaluating LLMs as Human-like Dialogue Systemscited by 31
  22. 2022A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learningcited by 30
  23. 2019A Dynamic Strategy Coach for Effective Negotiationcited by 26
  24. 2024Non-myopic Generation of Language Models for Reasoning and Planningcited by 26
  25. 2021Semantic Representation for Dialogue Modelingcited by 24
  26. 2023Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curationcited by 23
  27. 2020Keyword-Guided Neural Conversational Modelcited by 21
  28. 2023Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systemscited by 19
  29. 2023Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialoguecited by 14
  30. 2025Generating 3D Binding Molecules Using Shape-Conditioned Diffusion Models with Guidancecited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
  2. 2024Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models
  3. 2026Context-Agent: Dynamic Discourse Trees for Non-Linear Dialogue
  4. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
  5. 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents
  6. 2024Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner
  7. 2022Towards a Progression-Aware Autonomous Dialogue Agent
  8. 2024Sub-goal Distillation: A Method to Improve Small Language Agents