mlsanityData to 7 Oct 2026

Cognitive Architectures for Language Agents

arXiv 2309.02427 ↗First posted 5 Sep 2023cs.AI cs.CL cs.LGcited by 422

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

Abstract (arXiv)

Recent efforts have augmented large language models (LLMs) with external resources (e.g., the Internet) or internal control flows (e.g., prompt chaining) for tasks requiring grounding or reasoning, leading to a new class of language agents. While these agents have achieved substantial empirical success, we lack a systematic framework to organize existing agents and plan future developments. In this paper, we draw on the rich history of cognitive science and symbolic artificial intelligence to propose Cognitive Architectures for Language Agents (CoALA). CoALA describes a language agent with modular memory components, a structured action space to interact with internal memory and external environments, and a generalized decision-making process to choose actions. We use CoALA to retrospectively survey and organize a large body of recent work, and prospectively identify actionable directions towards more capable agents. Taken together, CoALA contextualizes today's language agents within the broader history of AI and outlines a path towards language-based general intelligence.

Key facts. Cited by 422 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 149 of its 235 references that are in the map. First posted on arXiv 5 Sep 2023.

Builds on

149 of 235 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  2. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  3. 2023Gentopia: A Collaborative Platform for Tool-Augmented LLMs8 Aug
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  5. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May
  6. 2023Towards autonomous system: flexible modular production system enhanced with large language model agents28 Apr
  7. 2022Language Models as Agent Models3 Dec

Other references · 142

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2022Training language models to follow instructions with human feedbackcited by 15,712
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  7. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  8. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  9. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  10. 2023Visual Instruction Tuningcited by 7,792
  11. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  12. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
38 more
  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  9. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  10. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  11. 2022Emergent Abilities of Large Language Modelscited by 2,483
  12. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  13. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  14. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  15. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  16. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  17. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  18. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  19. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  20. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  21. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  22. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  23. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  24. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  25. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  26. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  27. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  28. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  29. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  30. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  31. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  32. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  33. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  34. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  35. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  36. 2023Teaching Large Language Models to Self-Debugcited by 963
  37. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  38. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871

50 most cited of 142 All 142 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 23; 2024: 104; 2025: 110; 2026: 185.

422 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  3. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  4. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  5. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  6. 2024OS-ATLAS: A Foundation Action Model for Generalist GUI Agentscited by 370
  7. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  8. 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Taskscited by 289
  9. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 268
  10. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
  11. 2025SWE-smith: Scaling Data for Software Engineering Agentscited by 255
  12. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
38 more
  1. 2025GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agentscited by 240
  2. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  3. 2024Tool Learning with Large Language Models: A Surveycited by 221
  4. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  5. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  6. 2023You Only Look at Screens: Multimodal Chain-of-Action Agentscited by 185
  7. 2024Agent S: An Open Agentic Framework that Uses Computers Like a Humancited by 182
  8. 2025An Illusion of Progress? Assessing the Current State of Web Agentscited by 165
  9. 2023FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Designcited by 163
  10. 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fastcited by 149
  11. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
  12. 2023Large Language Models for Robotics: A Surveycited by 132
  13. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 128
  14. 2025Towards a Science of Scaling Agent Systemscited by 125
  15. 2024WebCanvas: Benchmarking Web Agents in Online Environmentscited by 119
  16. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 119
  17. 2024IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systemscited by 118
  18. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  19. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
  20. 2024A Survey on Large Language Model-Based Game Agentscited by 106
  21. 2023Evil Geniuses: Delving into the Safety of LLM-based Agentscited by 103
  22. 2024Large Multimodal Agents: A Surveycited by 99
  23. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Modelscited by 97
  24. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 96
  25. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 95
  26. 2024LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discoverycited by 82
  27. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  28. 2025Agent Learning via Early Experiencecited by 79
  29. 2023Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arenacited by 78
  30. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  31. 2024Visibility into AI Agentscited by 77
  32. 2024Building Machines that Learn and Think with Peoplecited by 73
  33. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  34. 2024BLADE: Benchmarking Language Model Agents for Data-Driven Sciencecited by 72
  35. 2024Can Language Models Solve Olympiad Programming?cited by 70
  36. 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
  37. 2024MedCalc-Bench: Evaluating Large Language Models for Medical Calculationscited by 64
  38. 2024Direct Multi-Turn Preference Optimization for Language Agentscited by 63

50 most cited of 422 All 422 (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. 2024Bootstrapping Cognitive Agents with a Large Language Model
  3. 2026The Path Ahead for Agentic AI: Challenges and Opportunities
  4. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
  5. 2023Exploiting Language Models as a Source of Knowledge for Cognitive Agents
  6. 2024Symbolic Learning Enables Self-Evolving Agents
  7. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
  8. 2023An In-depth Survey of Large Language Model-based Artificial Intelligence Agents