mlsanityData to 14 Oct 2026

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

arXiv 2401.12954 ↗First posted 23 Jan 2024cs.CL cs.AI cs.HCcited by 117

Not on the map. Why?

Cited by 42 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce meta-prompting, an effective scaffolding technique designed to enhance the functionality of language models (LMs). This approach transforms a single LM into a multi-faceted conductor, adept at managing and integrating multiple independent LM queries. By employing high-level instructions, meta-prompting guides the LM to break down complex tasks into smaller, more manageable subtasks. These subtasks are then handled by distinct "expert" instances of the same LM, each operating under specific, tailored instructions. Central to this process is the LM itself, in its role as the conductor, which ensures seamless communication and effective integration of the outputs from these expert models. It additionally employs its inherent critical thinking and robust verification processes to refine and authenticate the end result. This collaborative prompting approach empowers a single LM to simultaneously act as a comprehensive orchestrator and a panel of diverse experts, significantly enhancing its performance across a wide array of tasks. The zero-shot, task-agnostic nature of meta-prompting greatly simplifies user interaction by obviating the need for detailed, task-specific instructions. Furthermore, our research demonstrates the seamless integration of external tools, such as a Python interpreter, into the meta-prompting framework, thereby broadening its applicability and utility. Through rigorous experimentation with GPT-4, we establish the superiority of meta-prompting over conventional scaffolding methods: When averaged across all tasks, including the Game of 24, Checkmate-in-One, and Python Programming Puzzles, meta-prompting, augmented with a Python interpreter functionality, surpasses standard prompting by 17.1%, expert (dynamic) prompting by 17.3%, and multipersona prompting by 15.2%.

Key facts. Cited by 117 papers in the map (data through 14 Oct 2026). Builds on 56 of its 72 references that are in the map. First posted on arXiv 23 Jan 2024.

Builds on

56 of 72 references.

References · 56

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  7. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  8. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  9. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  10. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  11. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  12. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
38 more
  1. 2023PaLM 2 Technical Reportcited by 1,162
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
  3. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  4. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  6. 2023Teaching Large Language Models to Self-Debugcited by 988
  7. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  8. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  9. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  10. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  11. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  12. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  13. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  14. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 530
  15. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  16. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 388
  17. 2022Self-critiquing models for assisting human evaluatorscited by 380
  18. 2023Language Models can Solve Computer Taskscited by 372
  19. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  20. 2023Large Language Models as Tool Makerscited by 303
  21. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 301
  22. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
  23. 2022Generating Sequences by Learning to Self-Correctcited by 277
  24. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 248
  25. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 240
  26. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  27. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 207
  28. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 205
  29. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 196
  30. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  31. 2023REFLECT: Summarizing Robot Experiences for Failure Explanation and Correctioncited by 175
  32. 2022Ask Me Anything: A simple strategy for prompting language modelscited by 155
  33. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 148
  34. 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 142
  35. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 129
  36. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tangocited by 128
  37. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 111
  38. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 107

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 39; 2025: 56; 2026: 22.

117 papers.

Sort:

By area:

  1. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  2. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  3. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
  4. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 163
  5. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 121
  6. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 111
  7. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  8. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 77
  9. 2025Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoningcited by 63
  10. 2025MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agentscited by 62
  11. 2025Voting or Consensus? Decision-Making in Multi-Agent Debatecited by 59
  12. 2024AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviewscited by 44
38 more
  1. 2025CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimizationcited by 44
  2. 2024Adaptive In-conversation Team Building for Language Model Agentscited by 39
  3. 2024OSCAR: Operating System Control via State-Aware Reasoning and Re-Planningcited by 38
  4. 2025PENCIL: Long Thoughts with Short Memorycited by 33
  5. 2024Break the Chain: Large Language Models Can be Shortcut Reasonerscited by 32
  6. 2024LiteSearch: Efficacious Tree Search for LLMcited by 31
  7. 2025Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Modelscited by 31
  8. 2024Meta-Prompting for Automating Zero-shot Visual Recognition with LLMscited by 29
  9. 2024Meta Reasoning for Large Language Modelscited by 29
  10. 2024AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistantcited by 27
  11. 2024Automatic Instruction Evolving for Large Language Modelscited by 26
  12. 2024Instance-adaptive Zero-shot Chain-of-Thought Promptingcited by 26
  13. 2024Steering Large Language Models between Code Execution and Textual Reasoningcited by 24
  14. 2024Multi-Agent Large Language Models for Conversational Task-Solvingcited by 24
  15. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 24
  16. 2025Stay Focused: Problem Drift in Multi-Agent Debatecited by 23
  17. 2025Self-Evolving Multi-Agent Systems via Textual Backpropagationcited by 23
  18. 2024Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitationcited by 19
  19. 2024Infogent: An Agent-Based Framework for Web Information Aggregationcited by 19
  20. 2026GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Trainingcited by 18
  21. 2024Healthcare Copilot: Eliciting the Power of General LLMs for Medical Consultationcited by 17
  22. 2025Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planningcited by 17
  23. 2025MASTER: A Multi-Agent System with LLM Specialized MCTScited by 16
  24. 2025Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Thinkcited by 16
  25. 2025R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learningcited by 15
  26. 2025Literature Review Of Multi-Agent Debate For Problem-Solvingcited by 15
  27. 2025AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentationcited by 15
  28. 2024Exploring LLM Multi-Agents for ICD Codingcited by 14
  29. 2024IPO: Interpretable Prompt Optimization for Vision-Language Modelscited by 14
  30. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  31. 2025R3Mem: Bridging Memory Retention and Retrieval via Reversible Compressioncited by 12
  32. 2025CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidancecited by 11
  33. 2024Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimizationcited by 10
  34. 2024Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-upcited by 10
  35. 2025MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generationcited by 10
  36. 2025AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaborationcited by 10
  37. 2025Verification-Aware Planning for Multi-Agent Systemscited by 10
  38. 2025ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoningcited by 9

50 most cited of 117 All 117 (JSON)