mlsanityData to 14 Oct 2026

Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey

arXiv 2503.22458 ↗First posted 28 Mar 2025cs.CL cs.AIcited by 57

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

Abstract (arXiv)

This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings. Using a PRISMA-inspired framework, we systematically reviewed nearly 250 scholarly sources, capturing the state of the art from various venues of publication, and establishing a solid foundation for our analysis. Our study offers a structured approach by developing two interrelated taxonomy systems: one that defines what to evaluate and another that explains how to evaluate. The first taxonomy identifies key components of LLM-based agents for multi-turn conversations and their evaluation dimensions, including task completion, response quality, user experience, memory and context retention, as well as planning and tool integration. These components ensure that the performance of conversational agents is assessed in a holistic and meaningful manner. The second taxonomy system focuses on the evaluation methodologies. It categorizes approaches into annotation-based evaluations, automated metrics, hybrid strategies that combine human assessments with quantitative measures, and self-judging methods utilizing LLMs. This framework not only captures traditional metrics derived from language understanding, such as BLEU and ROUGE scores, but also incorporates advanced techniques that reflect the dynamic, interactive nature of multi-turn dialogues.

Key facts. Cited by 57 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 172 of its 264 references that are in the map. First posted on arXiv 28 Mar 2025.

Builds on

172 of 264 references.

Closest ancestors · 16

Same direction, newest first

  1. 2024Agent-as-a-Judge: Evaluate Agents with Agents14 Oct
  2. 2024LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner30 Sep
  3. 2024MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making25 Sep
  4. 2024Automated test generation to evaluate tool-augmented LLMs as conversational AI agents24 Sep
  5. 2024FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents21 Jun
  6. 2024Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner17 Jun
  7. 2024TwoStep: Multi-agent Task Planning using Classical Planners and Large Language Models25 Mar
  8. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments22 Feb
  9. 2024TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation15 Feb
  10. 2024Understanding the planning of LLM agents: A survey5 Feb
  11. 2024Should agentic conversational AI change how we think about ethics? Characterising an interactional ethics centred on respect17 Jan
  12. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents13 Oct
4 more
  1. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration3 Oct
  2. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  3. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  4. 2023AdaPlanner: Adaptive Planning from Feedback with Language Models26 May

Other references · 156

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  7. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  9. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  10. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  11. 2020Learning to summarize from human feedbackcited by 2,588
  12. 2017Billion-scale similarity search with GPUscited by 2,497
38 more
  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  2. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  3. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  4. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  5. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  6. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  7. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  8. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  9. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  10. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  11. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  12. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  13. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  14. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  15. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  16. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  17. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  18. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  19. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 461
  20. 2022Memory-Based Model Editing at Scalecited by 447
  21. 2024Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Expertscited by 376
  22. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 297
  23. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 274
  24. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  25. 2024MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialoguescited by 250
  26. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  27. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 217
  28. 2015A Neural Conversational Modelcited by 196
  29. 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 180
  30. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 177
  31. 2023Benchmarking Foundation Models with Language-Model-as-an-Examinercited by 172
  32. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  33. 2022Large Language Models with Controllable Working Memorycited by 169
  34. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  35. 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 140
  36. 2023User Behavior Simulation with Large Language Model based Agentscited by 140
  37. 2023Focused Transformer: Contrastive Training for Context Scalingcited by 133
  38. 2020Generating Fact Checking Explanationscited by 132

50 most cited of 156 All 156 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 22; 2026: 35.

57 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  2. 2025Drift No More? Context Equilibria in Multi-Turn LLM Interactionscited by 22
  3. 2026Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Taskscited by 19
  4. 2025Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchorscited by 14
  5. 2025Convomem Benchmark: Why Your First 150 Conversations Don't Need RAGcited by 10
  6. 2026From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Modelscited by 10
  7. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  8. 2025Routine: A Structural Planning Framework for LLM Agent System in Enterprisecited by 9
  9. 2025Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Modelscited by 9
  10. 2026TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modelingcited by 8
  11. 2025Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systemscited by 7
  12. 2026AI Agents Need Memory Control Over More Contextcited by 7
38 more
  1. 2025Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memorycited by 6
  2. 2026H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactionscited by 6
  3. 2025Evaluating Multi-Turn Bargain Skills in LLM-Based Seller Agentcited by 4
  4. 2026ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agentscited by 4
  5. 2026Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agentscited by 4
  6. 2025Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision Supportcited by 3
  7. 2025MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluationcited by 3
  8. 2025Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Promptingcited by 3
  9. 2025Investigating Symbolic Triggers of Hallucination in Gemma Models Across HaluEval and TruthfulQAcited by 3
  10. 2026AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystemcited by 3
  11. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challengescited by 3
  12. 2025Why do AI agents communicate in human language?cited by 2
  13. 2025Training Task Reasoning LLM Agents for Multi-turn Task Planning via Single-turn Reinforcement Learningcited by 2
  14. 2025Hey, wait a minute: on at-issue sensitivity in Language Modelscited by 2
  15. 2026Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Modelscited by 2
  16. 2026Counterfactual Fairness Evaluation of LLM-Based Contact Center Agent Quality Assurance Systemcited by 2
  17. 2026Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiencycited by 2
  18. 2026ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluationcited by 2
  19. 2026Multi2: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environmentscited by 2
  20. 2025Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmapcited by 1
  21. 2025When Users Are Happy but Agents Are Wrong: Multi-Dimensional Evaluation of Tool-Augmented Dialoguecited by 1
  22. 2026HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistantscited by 1
  23. 2026NC-Bench: An LLM Benchmark for Evaluating Conversational Competencecited by 1
  24. 2026ReIn: Conversational Error Recovery with Reasoning Inceptioncited by 1
  25. 2026Criterion Validity of LLM-as-Judge for Business Outcomes in Conversational Commercecited by 1
  26. 2026Optimus: Elastic Decoding for Efficient Diffusion LLM Servingcited by 1
  27. 2026SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreakscited by 1
  28. 2026Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challengescited by 1
  29. 2026Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agentscited by 1
  30. 2025CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLMcited by 0
  31. 2025Unsupervised Evaluation of Multi-Turn Objective-Driven Interactionscited by 0
  32. 2025Context informs pragmatic interpretation in vision-language modelscited by 0
  33. 2025Convergence of Outputs When Two Large Language Models Interact in a Multi-Agentic Setupcited by 0
  34. 2026Empathy Is Not What Changed: Clinical Assessment of Psychological Safety Across GPT Model Generationscited by 0
  35. 2026Automatic Analysis of Collaboration Through Human Conversational Data Resources: A Reviewcited by 0
  36. 2026SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphscited by 0
  37. 2026Measuring Semantic Progress in Multi-turn Dialogue via Information Gaincited by 0
  38. 2026SpheriCity: Designing Trustworthy Conversational AI for Sustainability Decision Supportcited by 0

50 most cited of 57 All 57 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate
  2. 2025MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators
  3. 2025Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
  4. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
  5. 2023AgentBench: Evaluating LLMs as Agents
  6. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study
  7. 2025Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
  8. 2025Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments