mlsanityData to 14 Oct 2026

Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models

arXiv 2504.04717 ↗First posted 7 Apr 2025cs.CL cs.AIcited by 62

Not on the map. Why?

Abstract (arXiv)

Recent advances in large language models (LLMs) have substantially improved single-turn task performance, yet real-world applications increasingly demand sophisticated multi-turn interactions. This survey provides a comprehensive review of recent progress in evaluating and enhancing multi-turn LLM interactions. Centered on a task-oriented taxonomy-spanning instruction following in domains such as mathematics and coding, and conversational engagement in role-playing, healthcare, education, and adversarial jailbreak settings-we systematically examine the challenges of maintaining context, coherence, fairness, and responsiveness across prolonged dialogues. We organize existing benchmarks and datasets into coherent categories reflecting the evolving landscape of multi-turn dialogue evaluation, and review a broad spectrum of enhancement methodologies, including model-centric strategies (in-context learning, supervised fine-tuning, reinforcement learning, and architectural innovations), external integration approaches (memory augmentation, retrieval-based methods, and knowledge graphs), and agent-based techniques for collaborative interaction. Finally, we identify open challenges and promising directions for future research to further improve the robustness and effectiveness of multi-turn LLM interactions.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Apr 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 25; 2026: 37.

62 papers.

Sort:

By area:

  1. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 75
  2. 2025The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating Itcited by 45
  3. 2025BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Designcited by 24
  4. 2025Get Experience from Practice: LLM Agents with Record & Replaycited by 23
  5. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 18
  6. 2026SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillationcited by 15
  7. 2025Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flowcited by 13
  8. 2026InfoPO: Information-Driven Policy Optimization for User-Centric Agentscited by 12
  9. 2025Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberationcited by 11
  10. 2025Conformal Information Pursuit for Interactively Guiding Large Language Modelscited by 7
  11. 2025Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systemscited by 7
  12. 2025FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Managementcited by 6
38 more
  1. 2025Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attackscited by 6
  2. 2026Attractor States Emerge in Multi-Turn LLM Conversationscited by 6
  3. 2025BrowseConf: Confidence-Guided Test-Time Scaling for Web Agentscited by 5
  4. 2026From History to State: Constant-Context Skill Learning for LLM Agentscited by 5
  5. 2026LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrailscited by 5
  6. 2025ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recoverycited by 4
  7. 2025Reducing Belief Deviation in Reinforcement Learning for Active Reasoningcited by 4
  8. 2026Consistency of Large Reasoning Models Under Multi-Turn Attackscited by 4
  9. 2026State-Dependent Safety Failures in Multi-Turn Language Model Interactioncited by 4
  10. 2025HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMscited by 3
  11. 2025KVCompose: Efficient Structured KV Cache Compression with Composite Tokenscited by 3
  12. 2025Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Promptingcited by 3
  13. 2025ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Cachingcited by 3
  14. 2025Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMscited by 3
  15. 2026Do Reasoning LLMs Refuse What They Infer in Long Contexts?cited by 3
  16. 2026Markovian Generation Chains in Large Language Modelscited by 3
  17. 2026SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systemscited by 3
  18. 2026Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideationcited by 3
  19. 2026SOTOPIA-TOM: Evaluating Privacy and Information Management in Multi-Agent Interaction with Theory of Mindcited by 3
  20. 2026MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attackscited by 3
  21. 2025LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluationcited by 2
  22. 2025Conversation Forests: The Key to Fine Tuning Large Language Models for Multi-Turn Medical Conversations is Branchingcited by 2
  23. 2025Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Explorationcited by 2
  24. 2026VOLMO: Versatile and Open Large Models for Ophthalmologycited by 2
  25. 2026SinkTrack: Attention Sink based Context Anchoring for Large Language Modelscited by 2
  26. 2026Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Servingcited by 2
  27. 2026SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoningcited by 2
  28. 2025MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learningcited by 1
  29. 2025A Criminology of Machinescited by 1
  30. 2025DREAM: Dynamic Red-teaming across Environments for AI Modelscited by 1
  31. 2026Learning to Learn from Language Feedback with Social Meta-Learningcited by 1
  32. 2026Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptationcited by 1
  33. 2026Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mindcited by 1
  34. 2026RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generatorcited by 1
  35. 2026EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agentscited by 1
  36. 2026The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressurecited by 1
  37. 2026DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimizationcited by 1
  38. 2026JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimizationcited by 1

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Multi-Turn Interaction Capabilities of Large Language Models
  2. 2026Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
  3. 2025Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs
  4. 2026Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs
  5. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey
  6. 2023Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models
  7. 2024Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
  8. 2025MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation