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

arXiv: https://arxiv.org/abs/2604.11427 · HTML: https://mlsanity.com/paper/2604.11427/

## 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 (most cited first, 30 of 34)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [Decoupling Strategy and Generation in Negotiation Dialogues](https://mlsanity.com/paper/1808.09637/) (2018)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents](https://mlsanity.com/paper/2311.00262/) (2023)
- [Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles](https://mlsanity.com/paper/2407.00870/) (2024)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning](https://mlsanity.com/paper/2305.13660/) (2023)
- [How to Build User Simulators to Train RL-based Dialog Systems](https://mlsanity.com/paper/1909.01388/) (2019)
- [Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering](https://mlsanity.com/paper/2211.03433/) (2022)
- [Let's Negotiate! A Survey of Negotiation Dialogue Systems](https://mlsanity.com/paper/2212.09072/) (2022)
- [A Dynamic Strategy Coach for Effective Negotiation](https://mlsanity.com/paper/1909.13426/) (2019)
- [Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation](https://mlsanity.com/paper/2403.06769/) (2024)
- [RESPER: Computationally Modelling Resisting Strategies in Persuasive Conversations](https://mlsanity.com/paper/2101.10545/) (2021)
- [Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy](https://mlsanity.com/paper/2204.07433/) (2022)
- [STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents](https://mlsanity.com/paper/2405.12059/) (2024)
- [PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents](https://mlsanity.com/paper/2509.17459/) (2025)
- [Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues](https://mlsanity.com/paper/2412.14584/) (2024)
- [Few-shot Dialogue Strategy Learning for Motivational Interviewing via Inductive Reasoning](https://mlsanity.com/paper/2403.15737/) (2024)
- [Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11](https://mlsanity.com/paper/2304.12982/) (2023)
- [Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factors](https://mlsanity.com/paper/2404.03304/) (2024)
- [Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction](https://mlsanity.com/paper/2410.18481/) (2024)
- [Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators](https://mlsanity.com/paper/2501.09484/) (2025)
- [DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning](https://mlsanity.com/paper/2505.03209/) (2025)
- [Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues](https://mlsanity.com/paper/2404.11095/) (2024)
- [Co-Matching: Towards Human-Machine Collaborative Legal Case Matching](https://mlsanity.com/paper/2405.10248/) (2024)
- [ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotation](https://mlsanity.com/paper/2405.11912/) (2024)
- [A Survey of Ontology Expansion for Conversational Understanding](https://mlsanity.com/paper/2410.15019/) (2024)

## Built on by (most cited first, 2 of 2)

- [How to Interpret Agent Behavior](https://mlsanity.com/paper/2605.13625/) (2026)
- [Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agents](https://mlsanity.com/paper/2605.22602/) (2026)

## 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.