Decoupling Strategy and Generation in Negotiation Dialogues
Not on the map. Why?
Cited by 37 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.
Abstract (arXiv)
We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing 50) and the execution of that strategy (e.g., generating "The bike is brand new. Selling for just 50."). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse di- alogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches.
Key facts. Cited by 156 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Aug 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 13; 2022: 13; 2023: 28; 2024: 34; 2025: 33; 2026: 35.
156 papers.
Sort:
By area:
- 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
- 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
- 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
- 2023Reward Design with Language Modelscited by 257
- 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoningcited by 145
- 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 115
- 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysiscited by 93
- 2023LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Modelscited by 84
- 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 76
- 2021Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systemscited by 73
- 2023A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospectscited by 66
- 2023Goal Driven Discovery of Distributional Differences via Language Descriptionscited by 61
38 more
- 2021CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systemscited by 60
- 2023Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planningcited by 60
- 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
- 2024NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surroundingcited by 49
- 2024Towards Human-centered Proactive Conversational Agentscited by 48
- 2024Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Methodcited by 44
- 2023Welfare Diplomacy: Benchmarking Language Model Cooperationcited by 43
- 2024Evaluating Language Model Agency through Negotiationscited by 43
- 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoningcited by 41
- 2023Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversationscited by 38
- 2022CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learningcited by 33
- 2024Planning Like Human: A Dual-process Framework for Dialogue Planningcited by 32
- 2022Let's Negotiate! A Survey of Negotiation Dialogue Systemscited by 31
- 2023Decision-Oriented Dialogue for Human-AI Collaborationcited by 29
- 2024Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialoguescited by 29
- 2021DeliData: A dataset for deliberation in multi-party problem solvingcited by 26
- 2021DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialoguescited by 25
- 2024A Survey on Recent Advances in Conversational Data Generationcited by 23
- 2022Context-Aware Language Modeling for Goal-Oriented Dialogue Systemscited by 22
- 2023DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AIcited by 21
- 2024Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulationcited by 21
- 2023ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessmentcited by 19
- 2021RESPER: Computationally Modelling Resisting Strategies in Persuasive Conversationscited by 18
- 2022Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policycited by 17
- 2025SOTOPIA-Omega: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agentscited by 16
- 2021Reference-Centric Models for Grounded Collaborative Dialoguecited by 15
- 2023Investigating Agency of LLMs in Human-AI Collaboration Taskscited by 15
- 2023Be Selfish, But Wisely: Investigating the Impact of Agent Personality in Mixed-Motive Human-Agent Interactionscited by 15
- 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agentscited by 15
- 2025Magentic Marketplace: An Open-Source Environment for Studying Agentic Marketscited by 15
- 2022Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Taskscited by 14
- 2024Efficacy of Language Model Self-Play in Non-Zero-Sum Gamescited by 14
- 2024Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrievalcited by 14
- 2024Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialoguescited by 14
- 2026A Survey on LLM-based Conversational User Simulationcited by 14
- 2022Opponent Modeling in Negotiation Dialogues by Related Data Adaptationcited by 13
- 2024ACE: A LLM-based Negotiation Coaching Systemcited by 13
- 2023Towards the Scalable Evaluation of Cooperativeness in Language Modelscited by 12
50 most cited of 156 All 156 (JSON)
- 2026Learning to Sell: Reinforcement Learning for Strategic Large Language Model Agents in Multi-Product Markets27 Sep 2026
- 2026Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation21 Sep 2026
- 2026STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution16 Sep 2026
- 2026ProMediConv: Benchmarking Proactive Conversational Agents in Legal Dispute Mediation10 Sep 2026
- 2026DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues6 Sep 2026
- 2026MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment14 Aug 2026
- 2026From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL13 Aug 2026
- 2026IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents7 Aug 2026
- 2026Can LLM Agents Price Competitively? A Dynamic Multi-Attribute Auction Benchmark for Agentic Commerce30 Jul 2026
- 2026DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues28 Jul 2026
- 2026Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection28 Jul 2026
- 2026Commitment To Cooperation With Self-Negotiated Contracts23 Jul 2026
38 more
- 2026SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure2 Jul 2026
- 2026DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents2 Jul 2026
- 2026Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce23 Jun 2026
- 2026SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations4 Jun 2026
- 2026Safe Equilibrium Policy Optimization for Strategic Agent Policies29 May 2026
- 2026EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation26 May 2026
- 2026Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators15 May 2026
- 2026Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling12 May 2026
- 2026SOMA: Efficient Multi-turn LLM Serving via Small Language Model11 May 2026
- 2026A Survey on LLM-based Conversational User Simulation27 Apr 2026
- 2026Anchor-and-Resume Concession Under Dynamic Pricing for LLM-Augmented Freight Negotiation22 Apr 2026
- 2026PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues20 Apr 2026
- 2026MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games14 Apr 2026
- 2026Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind13 Apr 2026
- 2026METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues13 Apr 2026
- 2026UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems7 Apr 2026
- 2026HCAG: Hierarchical Abstraction and Retrieval-Augmented Generation on Theoretical Repositories with LLMs19 Mar 2026
- 2026A Benchmark for Multi-Party Negotiation Games from Real Negotiation Data14 Mar 2026
- 2026Enhancing Persuasive Dialogue Agents by Synthesizing Cross-Disciplinary Communication Strategies26 Feb 2026
- 2026MERIT Feedback Elicits Better Bargaining in LLM Negotiators11 Feb 2026
- 2026AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions5 Feb 2026
- 2026PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios5 Feb 2026
- 2026The Language of Bargaining: Linguistic Effects in LLM Negotiations7 Jan 2026
- 2025Measuring Fine-Grained Negotiation Tactics of Humans and LLMs in Diplomacy20 Dec 2025
- 2025Characterizing Language Use in a Collaborative Situated Game3 Dec 2025
- 2025Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF26 Nov 2025
- 2025A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks17 Nov 2025
- 2025From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation16 Nov 2025
- 2025Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets27 Oct 2025
- 2025Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL16 Oct 2025
- 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents22 Sep 2025
- 2025We Argue to Agree: Towards Personality-Driven Argumentation-Based Negotiation Dialogue Systems for Tourism14 Sep 2025
- 2025Evaluating Multi-Turn Bargain Skills in LLM-Based Seller Agent8 Sep 2025
- 2025EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation4 Sep 2025
- 2025Emotionally-Aware Agents for Dispute Resolution28 Aug 2025
- 2025How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations28 Aug 2025
- 2025BASIL: Bayesian Assessment of Sycophancy in LLMs23 Aug 2025
- 2025Exploring Big Five Personality and AI Capability Effects in LLM-Simulated Negotiation Dialogues19 Jun 2025
50 newest of 156 All 156 (JSON)
- 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
- 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
- 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysiscited by 93
- 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 76
- 2025SOTOPIA-Omega: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agentscited by 16
- 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agentscited by 15
- 2025Magentic Marketplace: An Open-Source Environment for Studying Agentic Marketscited by 15
- 2024Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Plannercited by 12
- 2025The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Marketscited by 12
- 2026AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactionscited by 11
- 2025Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Gamecited by 10
- 2022Towards a Progression-Aware Autonomous Dialogue Agentcited by 7
12 most cited of 33 All 33 (JSON)
- 2026Learning to Sell: Reinforcement Learning for Strategic Large Language Model Agents in Multi-Product Markets27 Sep 2026
- 2026Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation21 Sep 2026
- 2026ProMediConv: Benchmarking Proactive Conversational Agents in Legal Dispute Mediation10 Sep 2026
- 2026Can LLM Agents Price Competitively? A Dynamic Multi-Attribute Auction Benchmark for Agentic Commerce30 Jul 2026
- 2026DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents2 Jul 2026
- 2026Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce23 Jun 2026
- 2026Safe Equilibrium Policy Optimization for Strategic Agent Policies29 May 2026
- 2026EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation26 May 2026
- 2026Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling12 May 2026
- 2026Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind13 Apr 2026
- 2026AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions5 Feb 2026
- 2026PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios5 Feb 2026
12 newest of 33 All 33 (JSON)
- 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoningcited by 145
- 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoningcited by 41
- 2023TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaborationcited by 11
- 2025Spontaneous Giving and Calculated Greed in Language Modelscited by 9
- 2025EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiationcited by 8
- 2025Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHFcited by 2
- 2026IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agentscited by 0
- 2026From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRLcited by 0
- 2026From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL13 Aug 2026
- 2026IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents7 Aug 2026
- 2025Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF26 Nov 2025
- 2025EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiation4 Sep 2025
- 2025Spontaneous Giving and Calculated Greed in Language Models24 Feb 2025
- 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning7 Feb 2025
- 2024MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning3 Jun 2024
- 2023TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaboration28 Sep 2023
- 2024Efficacy of Language Model Self-Play in Non-Zero-Sum Gamescited by 14
- 2024Efficacy of Language Model Self-Play in Non-Zero-Sum Games27 Jun 2024
- 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
- 2023Reward Design with Language Modelscited by 257
- 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 115
- 2023LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Modelscited by 84
- 2021Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systemscited by 73
- 2023A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospectscited by 66
- 2023Goal Driven Discovery of Distributional Differences via Language Descriptionscited by 61
- 2021CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systemscited by 60
- 2023Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planningcited by 60
- 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
- 2024NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surroundingcited by 49
- 2024Towards Human-centered Proactive Conversational Agentscited by 48
12 most cited of 107 All 107 (JSON)
- 2026STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution16 Sep 2026
- 2026DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues28 Jul 2026
- 2026Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection28 Jul 2026
- 2026Commitment To Cooperation With Self-Negotiated Contracts23 Jul 2026
- 2026SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure2 Jul 2026
- 2026SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations4 Jun 2026
- 2026Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators15 May 2026
- 2026A Survey on LLM-based Conversational User Simulation27 Apr 2026
- 2026Anchor-and-Resume Concession Under Dynamic Pricing for LLM-Augmented Freight Negotiation22 Apr 2026
- 2026PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues20 Apr 2026
- 2026MISID: A Multimodal Multi-turn Dataset for Complex Intent Recognition in Strategic Deception Games14 Apr 2026
- 2026METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues13 Apr 2026
12 newest of 107 All 107 (JSON)