mlsanityData to 7 Oct 2026

Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning

arXiv 2305.13660 ↗First posted 23 May 2023cs.CLcited by 60

Not on the map. Why?

Abstract (arXiv)

Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such as A* search and Monte Carlo Tree Search (MCTS). However, this training often requires abundant annotated data, which creates challenges when faced with noisy annotations or low-resource settings. We introduce GDP-Zero, an approach using Open-Loop MCTS to perform goal-oriented dialogue policy planning without any model training. GDP-Zero prompts a large language model to act as a policy prior, value function, user simulator, and system model during the tree search. We evaluate GDP-Zero on the goal-oriented task PersuasionForGood, and find that its responses are preferred over ChatGPT up to 59.32% of the time, and are rated more persuasive than ChatGPT during interactive evaluations.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 35 of its 58 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

35 of 58 references.

References · 35

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  4. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 849
  5. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  6. 2023How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detectioncited by 472
  7. 2021Towards Emotional Support Dialog Systemscited by 294
  8. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 207
  9. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  10. 2021Want To Reduce Labeling Cost? GPT-3 Can Helpcited by 196
  11. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 174
  12. 2023AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotatorscited by 171
23 more
  1. 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 166
  2. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 156
  3. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  4. 2023PLACES: Prompting Language Models for Social Conversation Synthesiscited by 72
  5. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  6. 2022Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planningcited by 59
  7. 2018Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systemscited by 53
  8. 2019How to Build User Simulators to Train RL-based Dialog Systemscited by 44
  9. 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
  10. 2023Controllable Mixed-Initiative Dialogue Generation through Promptingcited by 32
  11. 2017Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Modelscited by 26
  12. 2022Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Modelscited by 26
  13. 2018Zero-Shot Dialog Generation with Cross-Domain Latent Actionscited by 23
  14. 2022Multi-Stage Prompting for Knowledgeable Dialogue Generationcited by 22
  15. 2018Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learningcited by 21
  16. 2020Learning Goal-oriented Dialogue Policy with Opposite Agent Awarenesscited by 16
  17. 2021Schema-Guided Paradigm for Zero-Shot Dialogcited by 13
  18. 2021LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcingcited by 11
  19. 2022Seamlessly Integrating Factual Information and Social Content with Persuasive Dialoguecited by 11
  20. 2023Conversational Tree Search: A New Hybrid Dialog Taskcited by 7
  21. 2020Adaptive Dialog Policy Learning with Hindsight and User Modelingcited by 5
  22. 2022"Think Before You Speak": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogscited by 3
  23. 2023Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 20; 2025: 23; 2026: 16.

60 papers.

Sort:

By area:

  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 76
  3. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  4. 2024ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learningcited by 61
  5. 2025Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifierscited by 58
  6. 2024Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Trainingcited by 53
  7. 2024Towards Human-centered Proactive Conversational Agentscited by 48
  8. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  9. 2024Planning Like Human: A Dual-process Framework for Dialogue Planningcited by 32
  10. 2024RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Modelscited by 24
  11. 2024Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulationcited by 21
  12. 2025A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworkscited by 21
38 more
  1. 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agentscited by 15
  2. 2024Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialoguescited by 14
  3. 2025Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agentscited by 14
  4. 2024ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedbackcited by 13
  5. 2024FLAP: Flow-Adhering Planning with Constrained Decoding in LLMscited by 11
  6. 2024RoT: Enhancing Large Language Models with Reflection on Search Treescited by 11
  7. 2024ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agentscited by 11
  8. 2025Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RLcited by 11
  9. 2025Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Spacecited by 8
  10. 2025Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy Planningcited by 7
  11. 2025Dyna-Mind: Learning to Simulate from Experience for Better AI Agentscited by 7
  12. 2026Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent Systemcited by 7
  13. 2024PCQPR: Proactive Conversational Question Planning with Reflectioncited by 6
  14. 2025Feedback-Aware Monte Carlo Tree Search for Efficient Information Seeking in Goal-Oriented Conversationscited by 6
  15. 2025The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogscited by 6
  16. 2024SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generationcited by 5
  17. 2024SAPIENT: Mastering Multi-turn Conversational Recommendation with Strategic Planning and Monte Carlo Tree Searchcited by 5
  18. 2024Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerationscited by 5
  19. 2025Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewardscited by 5
  20. 2025AI Agents for Web Testing: A Case Study in the Wildcited by 5
  21. 2025DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulationcited by 5
  22. 2024The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trendscited by 4
  23. 2024Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Searchcited by 4
  24. 2025DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priorscited by 4
  25. 2025T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Searchcited by 4
  26. 2024Towards Goal-oriented Prompt Engineering for Large Language Models: A Surveycited by 3
  27. 2025Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Spacecited by 2
  28. 2025Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Searchcited by 2
  29. 2025Communication and Verification in LLM Agents towards Collaboration under Information Asymmetrycited by 2
  30. 2026METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialoguescited by 2
  31. 2026From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialoguecited by 2
  32. 2025Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervisioncited by 1
  33. 2025Tailored Conversations beyond LLMs: A RL-Based Dialogue Managercited by 1
  34. 2025Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignmentscited by 1
  35. 2025Mixed-Initiative Dialog for Human-Robot Collaborative Manipulationcited by 1
  36. 2025A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Taskscited by 1
  37. 2026Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategiescited by 1
  38. 2026Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversationscited by 1

50 most cited of 60 All 60 (JSON)