mlsanityData to 7 Oct 2026

Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control

arXiv 2306.07863 ↗First posted 13 Jun 2023cs.AIcited by 180

Not on the map. Why?

Cited by 126 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Building agents with large language models (LLMs) for computer control is a burgeoning research area, where the agent receives computer states and performs actions to complete complex tasks. Previous computer agents have demonstrated the benefits of in-context learning (ICL); however, their performance is hindered by several issues. First, the limited context length of LLMs and complex computer states restrict the number of exemplars, as a single webpage can consume the entire context. Second, the exemplars in current methods, such as high-level plans and multi-choice questions, cannot represent complete trajectories, leading to suboptimal performance in long-horizon tasks. Third, existing computer agents rely on task-specific exemplars and overlook the similarity among tasks, resulting in poor generalization to novel tasks. To address these challenges, we introduce Synapse, a computer agent featuring three key components: i) state abstraction, which filters out task-irrelevant information from raw states, allowing more exemplars within the limited context, ii) trajectory-as-exemplar prompting, which prompts the LLM with complete trajectories of the abstracted states and actions to improve multi-step decision-making, and iii) exemplar memory, which stores the embeddings of exemplars and retrieves them via similarity search for generalization to novel tasks. We evaluate Synapse on MiniWoB++, a standard task suite, and Mind2Web, a real-world website benchmark. In MiniWoB++, Synapse achieves a 99.2% average success rate (a 10% relative improvement) across 64 tasks using demonstrations from only 48 tasks. Notably, Synapse is the first ICL method to solve the book-flight task in MiniWoB++. Synapse also exhibits a 56% relative improvement in average step success rate over the previous state-of-the-art prompting scheme in Mind2Web.

Key facts. Cited by 180 papers in the map (data through 7 Oct 2026). Builds on 48 of its 69 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

48 of 69 references.

References · 48

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  9. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  10. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  11. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  12. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
36 more
  1. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  2. 2022Emergent Abilities of Large Language Modelscited by 2,483
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  5. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  7. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  9. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  10. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  11. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  12. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  13. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  14. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  15. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  16. 2023Teaching Large Language Models to Self-Debugcited by 963
  17. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  18. 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 598
  19. 2023Augmented Language Models: a Surveycited by 398
  20. 2023Language Models can Solve Computer Taskscited by 371
  21. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  22. 2018Reinforcement Learning on Web Interfaces Using Workflow-Guided Explorationcited by 282
  23. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 193
  24. 2020Mapping Natural Language Instructions to Mobile UI Action Sequencescited by 180
  25. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 174
  26. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  27. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Modelscited by 159
  28. 2021AndroidEnv: A Reinforcement Learning Platform for Androidcited by 90
  29. 2022A data-driven approach for learning to control computerscited by 87
  30. 2023From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfacescited by 67
  31. 2022Enabling Conversational Interaction with Mobile UI using Large Language Modelscited by 66
  32. 2018Learning to Navigate the Webcited by 60
  33. 2021Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learningcited by 40
  34. 2022Environment Generation for Zero-Shot Compositional Reinforcement Learningcited by 32
  35. 2023Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agentscited by 32
  36. 2019DOM-Q-NET: Grounded RL on Structured Languagecited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 38; 2025: 51; 2026: 88.

180 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  3. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 553
  4. 2024AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agentscited by 450
  5. 2024Agent Workflow Memorycited by 342
  6. 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactioncited by 271
  7. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  8. 2024On the Effects of Data Scale on UI Control Agentscited by 187
  9. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 182
  10. 2024Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMscited by 173
  11. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  12. 2024AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?cited by 155
38 more
  1. 2024OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesiscited by 155
  2. 2024The BrowserGym Ecosystem for Web Agent Researchcited by 152
  3. 2024Aria-UI: Visual Grounding for GUI Instructionscited by 136
  4. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  5. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  6. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigationcited by 116
  7. 2024Cradle: Empowering Foundation Agents Towards General Computer Controlcited by 114
  8. 2024GUICourse: From General Vision Language Models to Versatile GUI Agentscited by 112
  9. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  10. 2024AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agentscited by 110
  11. 2025Inducing Programmatic Skills for Agentic Taskscited by 103
  12. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Explorationcited by 100
  13. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 95
  14. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 91
  15. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  16. 2025Memp: Exploring Agent Procedural Memorycited by 88
  17. 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Modelscited by 87
  18. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  19. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  20. 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 71
  21. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
  22. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68
  23. 2023LASER: LLM Agent with State-Space Exploration for Web Navigationcited by 66
  24. 2023SteP: Stacked LLM Policies for Web Actionscited by 66
  25. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolutioncited by 65
  26. 2024Large Language Models Empowered Personalized Web Agentscited by 64
  27. 2025A Survey on (M)LLM-Based GUI Agentscited by 61
  28. 2025A Survey on Large Language Models for Mathematical Reasoningcited by 52
  29. 2024Ferret-UI 2: Mastering Universal User Interface Understanding Across Platformscited by 51
  30. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  31. 2025Contextual Experience Replay for Self-Improvement of Language Agentscited by 46
  32. 2024AgentStudio: A Toolkit for Building General Virtual Agentscited by 45
  33. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 45
  34. 2025Web-Shepherd: Advancing PRMs for Reinforcing Web Agentscited by 41
  35. 2025Magentic-UI: Towards Human-in-the-loop Agentic Systemscited by 41
  36. 2026Code as Agent Harnesscited by 40
  37. 2025LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automationcited by 39
  38. 2024CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agentscited by 38

50 most cited of 180 All 180 (JSON)