mlsanityData to 7 Oct 2026

SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue

arXiv 2602.03548 ↗First posted 3 Feb 2026cs.CLcited by 6

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

also in 1 more
Abstract (arXiv)

Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely on noisy, low-quality human conversation data. This limitation arises from data scarcity and the difficulty of simulating authentic, goal-oriented user behaviors. To address these issues, we propose SEAD (Self-Evolving Agent for Service Dialogue), a framework that enables agents to learn effective strategies without large-scale human annotations. SEAD decouples user modeling into two components: a Profile Controller that generates diverse user states to manage training curriculum, and a User Role-play Model that focuses on realistic role-playing. This design ensures the environment provides adaptive training scenarios rather than acting as an unfair adversary. Experiments demonstrate that SEAD significantly outperforms Open-source Foundation Models and Closed-source Commercial Models, improving task completion rate by 17.6% and dialogue efficiency by 11.1%. Code is available at: https://github.com/Da1yuqin/SEAD.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 27 of its 43 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

27 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning20 Nov
  2. 2025MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents7 Jul

Other references · 25

  1. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  2. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  3. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 323
  4. 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
  5. 2023Using an LLM to Help With Code Understandingcited by 222
  6. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 210
  7. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  8. 2015A Neural Conversational Modelcited by 195
  9. 2015Neural Responding Machine for Short-Text Conversationcited by 124
  10. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 95
  11. 2016A User Simulator for Task-Completion Dialoguescited by 56
  12. 2024Towards Human-centered Proactive Conversational Agentscited by 48
13 more
  1. 2024AGILE: A Novel Reinforcement Learning Framework of LLM Agentscited by 45
  2. 2025Learning to Solve and Verify: A Self-Play Framework for Code and Test Generationcited by 34
  3. 2025Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGIcited by 34
  4. 2023DialogBench: Evaluating LLMs as Human-like Dialogue Systemscited by 31
  5. 2025ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?cited by 27
  6. 2020Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluationcited by 19
  7. 2023MG-ShopDial: A Multi-Goal Conversational Dataset for e-Commercecited by 19
  8. 2024Exploring Multi-Lingual Bias of Large Code Models in Code Generationcited by 17
  9. 2025Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCRcited by 12
  10. 2025Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branchingcited by 10
  11. 2025Evaluating, Synthesizing, and Enhancing for Customer Support Conversationcited by 7
  12. 2022Toward An Optimal Selection of Dialogue Strategies: A Target-Driven Approach for Intelligent Outbound Robotscited by 2
  13. 2025NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Unlocking Proactivity in Task-Oriented Dialoguecited by 1
  2. 2026Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Designcited by 1
  3. 2026ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversationscited by 0
  4. 2026SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedbackcited by 0
  5. 2026GLARE: Generative Learning via Adversarial Reward Estimation For Social Dynamics Forecastingcited by 0
  6. 2026SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
  2. 2024DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems
  3. 2026Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPO
  4. 2024Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations
  5. 2025Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
  6. 2026From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
  7. 2024Adaptive In-conversation Team Building for Language Model Agents
  8. 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems