mlsanityData to 14 Oct 2026

PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents

arXiv 2509.17459 ↗First posted 22 Sep 2025cs.CLcited by 15

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Dialogue agents based on large language models (LLMs) have shown promising performance in proactive dialogue, which requires effective strategy planning. However, existing approaches to strategy planning for proactive dialogue face several limitations: limited strategy coverage, preference bias in planning, and reliance on costly additional training. To address these, we propose PRINCIPLES: a synthetic strategy memory for proactive dialogue agents. PRINCIPLES is derived through offline self-play simulations and serves as reusable knowledge that guides strategy planning during inference, eliminating the need for additional training and data annotation. We evaluate PRINCIPLES in both emotional support and persuasion domains, demonstrating consistent improvements over strong baselines. Furthermore, PRINCIPLES maintains its robustness across extended and more diverse evaluation settings. See our project page at https://huggingface.co/spaces/kimnamssya/Principles.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 20 of its 23 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

20 of 23 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Ask-before-Plan: Proactive Language Agents for Real-World Planning18 Jun
  2. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents1 Nov

Other references · 18

  1. 2021Towards Emotional Support Dialog Systemscited by 299
  2. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  3. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 209
  4. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 207
  5. 2018Decoupling Strategy and Generation in Negotiation Dialoguescited by 162
  6. 2023Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationcited by 116
  7. 2024Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principlescited by 73
  8. 2023A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospectscited by 66
  9. 2023Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planningcited by 61
  10. 2024Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversationcited by 55
  11. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 51
  12. 2023Controllable Mixed-Initiative Dialogue Generation through Promptingcited by 32
6 more
  1. 2024Planning Like Human: A Dual-process Framework for Dialogue Planningcited by 32
  2. 2023Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Modelscited by 31
  3. 2024Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulationcited by 21
  4. 2024Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialoguescited by 14
  5. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  6. 2025Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy Planningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 13.

15 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 49
  3. 2026RealMem: Benchmarking LLMs in Real-World Memory-Driven Interactioncited by 20
  4. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  5. 2026AdaMEM: Test-Time Adaptive Memory for Language Agentscited by 6
  6. 2026ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agentscited by 3
  7. 2026METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialoguescited by 2
  8. 2026Towards Direct Evaluation of Harness Optimizers via Priority Rankingcited by 2
  9. 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agentscited by 1
  10. 2026CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Spacecited by 0
  11. 2026Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversationscited by 0
  12. 2026User-Aware Active Knowledge Acquisition for Emotional Support Dialoguecited by 0
3 more
  1. 2026Experience Memory Graph: One-Shot Error Correction for Agentscited by 0
  2. 2026Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiencycited by 0
  3. 2026Proactive Dialogue Policy Optimization via Cognitive-State Transitioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  2. 2025ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
  3. 2024Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations
  4. 2025Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs
  5. 2025SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
  6. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  7. 2024"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents
  8. 2026LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation