mlsanityData to 14 Oct 2026

Language Models can Solve Computer Tasks

arXiv 2303.17491 ↗First posted 30 Mar 2023cs.CL cs.AI cs.HCcited by 372

Not on the map. Why?

Cited by 140 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Agents capable of carrying out general tasks on a computer can improve efficiency and productivity by automating repetitive tasks and assisting in complex problem-solving. Ideally, such agents should be able to solve new computer tasks presented to them through natural language commands. However, previous approaches to this problem require large amounts of expert demonstrations and task-specific reward functions, both of which are impractical for new tasks. In this work, we show that a pre-trained large language model (LLM) agent can execute computer tasks guided by natural language using a simple prompting scheme where the agent Recursively Criticizes and Improves its output (RCI). The RCI approach significantly outperforms existing LLM methods for automating computer tasks and surpasses supervised learning (SL) and reinforcement learning (RL) approaches on the MiniWoB++ benchmark. We compare multiple LLMs and find that RCI with the InstructGPT-3+RLHF LLM is state-of-the-art on MiniWoB++, using only a handful of demonstrations per task rather than tens of thousands, and without a task-specific reward function. Furthermore, we demonstrate RCI prompting's effectiveness in enhancing LLMs' reasoning abilities on a suite of natural language reasoning tasks, outperforming chain of thought (CoT) prompting with external feedback. We find that RCI combined with CoT performs better than either separately. Our code can be found here: https://github.com/posgnu/rci-agent.

Key facts. Cited by 372 papers in the map (data through 14 Oct 2026). Builds on 68 of its 82 references that are in the map. First posted on arXiv 30 Mar 2023.

Builds on

68 of 82 references.

References · 68

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  10. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  11. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  12. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
38 more
  1. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  2. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  3. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  4. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  5. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  6. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  7. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  9. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  10. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  11. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  12. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  13. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  14. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  15. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 897
  16. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  17. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  18. 2022A Generalist Agentcited by 808
  19. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  20. 2022Transformers learn in-context by gradient descentcited by 732
  21. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  22. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 622
  23. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 559
  24. 2022Improving alignment of dialogue agents via targeted human judgementscited by 531
  25. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  26. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  27. 2023Augmented Language Models: a Surveycited by 403
  28. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  29. 2022Self-critiquing models for assisting human evaluatorscited by 380
  30. 2016Solving General Arithmetic Word Problemscited by 360
  31. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 345
  32. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  33. 2022Teaching language models to support answers with verified quotescited by 292
  34. 2018Reinforcement Learning on Web Interfaces Using Workflow-Guided Explorationcited by 284
  35. 2022Generating Sequences by Learning to Self-Correctcited by 277
  36. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 197
  37. 2023Grounding Large Language Models in Interactive Environments with Online Reinforcement Learningcited by 195
  38. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 173

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 85; 2024: 144; 2025: 103; 2026: 40.

372 papers.

Sort:

By area:

  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  2. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  3. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  5. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  6. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  7. 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
  8. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  9. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  10. 2023Teaching Large Language Models to Self-Debugcited by 988
  11. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  12. 2023Large Language Models as Optimizerscited by 864
38 more
  1. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  2. 2023Instruction Tuning with GPT-4cited by 686
  3. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  4. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  5. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 567
  6. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  7. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 563
  8. 2024AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agentscited by 468
  9. 2023Cognitive Architectures for Language Agentscited by 429
  10. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
  11. 2024Understanding the planning of LLM agents: A surveycited by 421
  12. 2024Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agentscited by 382
  13. 2024WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?cited by 363
  14. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 353
  15. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMscited by 338
  16. 2023Android in the Wild: A Large-Scale Dataset for Android Device Controlcited by 319
  17. 2023How Language Model Hallucinations Can Snowballcited by 311
  18. 2023Large Language Models as Tool Makerscited by 303
  19. 2023Tool Learning with Foundation Modelscited by 302
  20. 2024Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactioncited by 278
  21. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  22. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  23. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  24. 2024Tool Learning with Large Language Models: A Surveycited by 223
  25. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  26. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 196
  27. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 195
  28. 2024On the Effects of Data Scale on UI Control Agentscited by 194
  29. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 187
  30. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 187
  31. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  32. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  33. 2024WebLINX: Real-World Website Navigation with Multi-Turn Dialoguecited by 180
  34. 2024Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMscited by 176
  35. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
  36. 2024Large Language Model-Brained GUI Agents: A Surveycited by 162
  37. 2024The BrowserGym Ecosystem for Web Agent Researchcited by 161
  38. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Modelscited by 160

50 most cited of 372 All 372 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
  2. 2024Reinforcement Learning Problem Solving with Large Language Models
  3. 2024From Language Models to Practical Self-Improving Computer Agents
  4. 2025Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent
  5. 2026Skill-R1: Agent Skill Evolution via Reinforcement Learning
  6. 2023StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
  7. 2026Computer Environments Elicit General Agentic Intelligence in LLMs
  8. 2026AutoTrainess: Teaching Language Models to Improve Language Models Autonomously