mlsanityData to 14 Oct 2026

METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues

arXiv 2604.11427 ↗First posted 13 Apr 2026cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Developing non-collaborative dialogue agents traditionally requires the manual, unscalable codification of expert strategies. We propose ours, a method that leverages large language models to autonomously induce both strategy actions and planning logic directly from raw transcripts. METRO formalizes expert knowledge into a Strategy Forest, a hierarchical structure that captures both short-term responses (nodes) and long-term strategic foresight (branches). Experimental results across two benchmarks show that METRO demonstrates promising performance, outperforming existing methods by an average of 9%-10%. Our further analysis not only reveals the success behind METRO (strategic behavioral diversity and foresight), but also demonstrates its robust cross-task transferability. This offers new insights into building non-collaborative agents in a cost-effective and scalable way. Our code is available at https://github.com/Humphrey-0125/METRO.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 64 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

34 of 64 references.

References · 34

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 209
  3. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 207
  4. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 162
  5. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 116
  6. 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysiscited by 100
  7. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 77
  8. 2024Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principlescited by 73
  9. 2023A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospectscited by 66
  10. 2023Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planningcited by 61
  11. 2019How to Build User Simulators to Train RL-based Dialog Systemscited by 46
  12. 2022Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Counteringcited by 40
22 more
  1. 2022Let's Negotiate! A Survey of Negotiation Dialogue Systemscited by 31
  2. 2019A Dynamic Strategy Coach for Effective Negotiationcited by 26
  3. 2024Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulationcited by 21
  4. 2021RESPER: Computationally Modelling Resisting Strategies in Persuasive Conversationscited by 19
  5. 2022Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policycited by 17
  6. 2024STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agentscited by 17
  7. 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agentscited by 15
  8. 2024Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialoguescited by 14
  9. 2024Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoningcited by 11
  10. 2023Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11cited by 10
  11. 2024Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factorscited by 9
  12. 2024Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extractioncited by 8
  13. 2025Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulatorscited by 8
  14. 2025DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learningcited by 7
  15. 2024Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialoguescited by 6
  16. 2024Co-Matching: Towards Human-Machine Collaborative Legal Case Matchingcited by 6
  17. 2024ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotationcited by 6
  18. 2024A Survey of Ontology Expansion for Conversational Understandingcited by 6
  19. 2024Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logiccited by 5
  20. 2024Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decodingcited by 5
  21. 2025Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agentscited by 5
  22. 2025Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactionscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026How to Interpret Agent Behaviorcited by 10
  2. 2026Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agentscited by 2