mlsanityData to 14 Oct 2026

A Survey on Multi-Turn Interaction Capabilities of Large Language Models

arXiv 2501.09959 ↗First posted 17 Jan 2025cs.CLcited by 30

Not on the map. Why?

Abstract (arXiv)

Multi-turn interaction in the dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling it to generate coherent and contextually relevant responses. Recent advancements in large language models (LLMs) have significantly expanded the scope of multi-turn interaction, moving beyond chatbots to enable more dynamic agentic interactions with users or environments. In this paper, we provide a focused review of the multi-turn capabilities of LLMs, which are critical for a wide range of downstream applications, including conversational search and recommendation, consultation services, and interactive tutoring. This survey explores four key aspects: (1) the core model capabilities that contribute to effective multi-turn interaction, (2) how multi-turn interaction is evaluated in current practice, (3) the general algorithms used to enhance multi-turn interaction, and (4) potential future directions for research in this field.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Jan 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: 19; 2026: 11.

30 papers.

Sort:

By area:

  1. 2025CollabLLM: From Passive Responders to Active Collaboratorscited by 124
  2. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 57
  3. 2025StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turnscited by 20
  4. 2025Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchorscited by 14
  5. 2026CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Usecited by 14
  6. 2025A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoningcited by 11
  7. 2025Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberationcited by 11
  8. 2025Charts Are Not Images: On the Challenges of Scientific Chart Editingcited by 11
  9. 2025Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMscited by 10
  10. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  11. 2025Evaluating the Sensitivity of LLMs to Prior Contextcited by 9
  12. 2025Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Modelscited by 9
18 more
  1. 2025Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactionscited by 6
  2. 2025ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Modelscited by 4
  3. 2026Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agentscited by 4
  4. 2026State-Dependent Safety Failures in Multi-Turn Language Model Interactioncited by 4
  5. 2025HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMscited by 3
  6. 2025Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMscited by 3
  7. 2025A Principle-based Framework for the Development and Evaluation of Large Language Models for Health and Wellnesscited by 3
  8. 2026A Framework for Longitudinal Health AI Agentscited by 3
  9. 2026Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversationscited by 3
  10. 2026MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attackscited by 3
  11. 2025Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Explorationcited by 2
  12. 2026Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gapcited by 2
  13. 2025Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Modelscited by 1
  14. 2025KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computingcited by 1
  15. 2026Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detectioncited by 1
  16. 2026Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversioncited by 1
  17. 2026SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreakscited by 1
  18. 2026ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
  2. 2026Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs
  3. 2025ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models
  4. 2026SOMA: Efficient Multi-turn LLM Serving via Small Language Model
  5. 2023Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models
  6. 2025MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
  7. 2024Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
  8. 2025Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model