mlsanityData to 7 Oct 2026

Language Models as Agent Models

arXiv 2212.01681 ↗First posted 3 Dec 2022cs.CL cs.MAcited by 131

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

Abstract (arXiv)

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of the internal states of the agents that produced them -- a fact often used to argue that LMs are incapable of modeling goal-directed aspects of human language production and comprehension. Can LMs trained on text learn anything at all about the relationship between language and use? I argue that LMs are models of intentional communication in a specific, narrow sense. When performing next word prediction given a textual context, an LM can infer and represent properties of an agent likely to have produced that context. These representations can in turn influence subsequent LM generation in the same way that agents' communicative intentions influence their language. I survey findings from the recent literature showing that -- even in today's non-robust and error-prone models -- LMs infer and use representations of fine-grained communicative intentions and more abstract beliefs and goals. Despite the limited nature of their training data, they can thus serve as building blocks for systems that communicate and act intentionally.

Key facts. Cited by 131 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 24 of its 44 references that are in the map. First posted on arXiv 3 Dec 2022.

Builds on

24 of 44 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  7. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  8. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  9. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  10. 2018Universal Transformerscited by 613
  11. 2019Defending Against Neural Fake Newscited by 553
  12. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
12 more
  1. 2021Causal Abstractions of Neural Networkscited by 401
  2. 2020Experience Grounds Languagecited by 241
  3. 2021Implicit Representations of Meaning in Neural Language Modelscited by 179
  4. 2017Learning to Generate Reviews and Discovering Sentimentcited by 147
  5. 2021Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefscited by 79
  6. 2022Meaning without reference in large language modelscited by 76
  7. 2020Limitations of Autoregressive Models and Their Alternativescited by 54
  8. 2016Tracking the World State with Recurrent Entity Networkscited by 51
  9. 2020Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Modelscited by 44
  10. 2021Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planningcited by 43
  11. 2021Sorting through the noise: Testing robustness of information processing in pre-trained language modelscited by 27
  12. 2022When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to itcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 50; 2024: 35; 2025: 27; 2026: 17.

131 papers.

Sort:

By area:

  1. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  2. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  3. 2024Refusal in Language Models Is Mediated by a Single Directioncited by 960
  4. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  5. 2023Cognitive Architectures for Language Agentscited by 422
  6. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  7. 2023Role-Play with Large Language Modelscited by 290
  8. 2023Can Language Models Solve Graph Problems in Natural Language?cited by 249
  9. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 211
  10. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
  11. 2023Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attackscited by 156
  12. 2023Fundamental Limitations of Alignment in Large Language Modelscited by 152
38 more
  1. 2023Chain of Hindsight Aligns Language Models with Feedbackcited by 147
  2. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 134
  3. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  4. 2024Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervisioncited by 95
  5. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 94
  6. 2023Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arenacited by 78
  7. 2023Training Socially Aligned Language Models on Simulated Social Interactionscited by 77
  8. 2023How FaR Are Large Language Models From Agents with Theory-of-Mind?cited by 75
  9. 2023Eight Things to Know about Large Language Modelscited by 73
  10. 2022A fine-grained comparison of pragmatic language understanding in humans and language modelscited by 69
  11. 2024Can Large Language Model Agents Simulate Human Trust Behavior?cited by 62
  12. 2023Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planningcited by 59
  13. 2024Are Large Language Models Consistent over Value-laden Questions?cited by 58
  14. 2023Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neuronscited by 56
  15. 2023SALMON: Self-Alignment with Instructable Reward Modelscited by 54
  16. 2023Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agentscited by 52
  17. 2023Large Language Models as Superpositions of Cultural Perspectivescited by 48
  18. 2025Why human-AI relationships need socioaffective alignmentcited by 47
  19. 2023Personas as a Way to Model Truthfulness in Language Modelscited by 46
  20. 2024Evaluating Language Model Agency through Negotiationscited by 43
  21. 2024Who's asking? User personas and the mechanics of latent misalignmentcited by 40
  22. 2023SoK: Memorization in General-Purpose Large Language Modelscited by 36
  23. 2025Consistently Simulating Human Personas with Multi-Turn Reinforcement Learningcited by 35
  24. 2025InSTA: Towards Internet-Scale Training For Agentscited by 31
  25. 2025Linear Representations of Political Perspective Emerge in Large Language Modelscited by 30
  26. 2025The Traitors: Deception and Trust in Multi-Agent Language Model Simulationscited by 30
  27. 2024AI for social science and social science of AI: A Surveycited by 29
  28. 2023Dissociating language and thought in large language modelscited by 27
  29. 2024LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunitiescited by 27
  30. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  31. 2023LLMs as Hackers: Autonomous Linux Privilege Escalation Attackscited by 25
  32. 2023CHORUS: Foundation Models for Unified Data Discovery and Explorationcited by 24
  33. 2023The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agentscited by 24
  34. 2024Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?cited by 24
  35. 2024A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debatescited by 22
  36. 2023Passive learning of active causal strategies in agents and language modelscited by 21
  37. 2023Towards Evaluating AI Systems for Moral Status Using Self-Reportscited by 21
  38. 2023Creating a Large Language Model of a Philosophercited by 20

50 most cited of 131 All 131 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Position: Stop Acting Like Language Model Agents Are Normal Agents
  2. 2026Beliefs and Behavior in Language Models
  3. 2025Are Large Language Models Sensitive to the Motives Behind Communication?
  4. 2025Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation
  5. 2025Accumulating Context Changes the Beliefs of Language Models
  6. 2023Augmenting Autotelic Agents with Large Language Models
  7. 2026From Tokens To Agents: A Researcher's Guide To Understanding Large Language Models
  8. 2025Why do AI agents communicate in human language?