mlsanityData to 14 Oct 2026

AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems

arXiv 2402.08995 ↗First posted 14 Feb 2024cs.HC cs.AIcited by 23

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Recently, Large Language Model based Autonomous system(LLMAS) has gained great popularity for its potential to simulate complicated behaviors of human societies. One of its main challenges is to present and analyze the dynamic events evolution of LLMAS. In this work, we present a visualization approach to explore detailed statuses and agents' behavior within LLMAS. We propose a general pipeline that establishes a behavior structure from raw LLMAS execution events, leverages a behavior summarization algorithm to construct a hierarchical summary of the entire structure in terms of time sequence, and a cause trace method to mine the causal relationship between agent behaviors. We then develop AgentLens, a visual analysis system that leverages a hierarchical temporal visualization for illustrating the evolution of LLMAS, and supports users to interactively investigate details and causes of agents' behaviors. Two usage scenarios and a user study demonstrate the effectiveness and usability of our AgentLens.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 51 of its 94 references that are in the map. First posted on arXiv 14 Feb 2024.

Builds on

51 of 94 references.

References · 51

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  9. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  10. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  11. 2022Emergent Abilities of Large Language Modelscited by 2,512
  12. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
38 more
  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  2. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  5. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  6. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  7. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  8. 2023Mastering Diverse Domains through World Modelscited by 1,253
  9. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  10. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  11. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  12. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  13. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
  14. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  15. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  16. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
  17. 2023Tool Learning with Foundation Modelscited by 302
  18. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 301
  19. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 289
  20. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 237
  21. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 233
  22. 2022Interactive Language: Talking to Robots in Real Timecited by 218
  23. 2019Interactive Fiction Games: A Colossal Adventurecited by 168
  24. 2023Emergent autonomous scientific research capabilities of large language modelscited by 132
  25. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Modelscited by 98
  26. 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modellingcited by 88
  27. 2023AgentSims: An Open-Source Sandbox for Large Language Model Evaluationcited by 88
  28. 2023PromptMagician: Interactive Prompt Engineering for Text-to-Image Creationcited by 58
  29. 2023Epidemic Modeling with Generative Agentscited by 49
  30. 2023Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Modelscited by 47
  31. 2023CGMI: Configurable General Multi-Agent Interaction Frameworkcited by 42
  32. 2022AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environmentscited by 26
  33. 2020Playing Text-Based Games with Common Sensecited by 21
  34. 2023XNLI: Explaining and Diagnosing NLI-based Visual Data Analysiscited by 19
  35. 2020Survey on Visual Analysis of Event Sequence Datacited by 10
  36. 2020Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoFcited by 6
  37. 2023Agents meet OKR: An Object and Key Results Driven Agent System with Hierarchical Self-Collaboration and Self-Evaluationcited by 6
  38. 2019Visual Analytics of Anomalous User Behaviors: A Surveycited by 4

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 6; 2026: 13.

23 papers.

Sort:

By area:

  1. 2024Exploring Autonomous Agents through the Lens of Large Language Models: A Reviewcited by 31
  2. 2024AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaborationcited by 26
  3. 2025Embodied AI: From LLMs to World Modelscited by 24
  4. 2025Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspectivecited by 13
  5. 2026AgentStepper: Interactive Debugging of Software Development Agentscited by 9
  6. 2024Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agentscited by 8
  7. 2026TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectoriescited by 8
  8. 2024JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Modelscited by 7
  9. 2026MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signalscited by 6
  10. 2025Carbon and Silicon, Coexist or Compete? A Survey on Human-AI Interactions in Agent-based Modeling and Simulationcited by 3
  11. 2025XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generationcited by 2
  12. 2026"What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agentscited by 2
11 more
  1. 2026TraceView: Interactive Visualization of Agentic Program Repair Trajectoriescited by 2
  2. 2026EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environmentscited by 2
  3. 2025OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaborationcited by 1
  4. 2025Story Ribbons: Reimagining Storyline Visualizations with Large Language Modelscited by 1
  5. 2026InconLens: Interactive Visual Diagnosis of Behavioral Inconsistencies in LLM-based Agentic Systemscited by 1
  6. 2026Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectoriescited by 1
  7. 2026Within the MDT Room: Situated in Multidisciplinary Team-Grounded Agent Debate for Clinical Diagnosiscited by 0
  8. 2026AgentGUI: An Interface for Observing and Steering Long-Running AI Agentscited by 0
  9. 2026Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysiscited by 0
  10. 2026FootprintRAG: Visual Analytics for Evidence Context Refinement in RAG-based Scientific Literature Explorationcited by 0
  11. 2026ParallelPilot: Supporting Coordination and Monitoring in Parallel AI Codingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors
  2. 2026AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis
  3. 2025A Visualized Framework for Event Cooperation with Generative Agents
  4. 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective
  5. 2025Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement
  6. 2026ATLAS: Discovering Agent Strategies through LLM-Guided Abstraction and Automata Learning
  7. 2026MyAG: A Graph-Based Framework for Designing and Analyzing Composable LLM Agent Systems
  8. 2024Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Dataset