mlsanityData to 7 Oct 2026

Building Machines that Learn and Think with People

arXiv 2408.03943 ↗First posted 22 Jul 2024cs.HC cs.AI cs.LGcited by 73

Not on the map. Why?

Abstract (arXiv)

What do we want from machine intelligence? We envision machines that are not just tools for thought, but partners in thought: reasonable, insightful, knowledgeable, reliable, and trustworthy systems that think with us. Current artificial intelligence (AI) systems satisfy some of these criteria, some of the time. In this Perspective, we show how the science of collaborative cognition can be put to work to engineer systems that really can be called ``thought partners,'' systems built to meet our expectations and complement our limitations. We lay out several modes of collaborative thought in which humans and AI thought partners can engage and propose desiderata for human-compatible thought partnerships. Drawing on motifs from computational cognitive science, we motivate an alternative scaling path for the design of thought partners and ecosystems around their use through a Bayesian lens, whereby the partners we construct actively build and reason over models of the human and world.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Builds on 87 of its 272 references that are in the map. First posted on arXiv 22 Jul 2024.

Builds on

87 of 272 references.

References · 87

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  4. 2017Deep reinforcement learning from human preferencescited by 3,846
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  8. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  10. 2016Concrete Problems in AI Safetycited by 1,582
  11. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  12. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
38 more
  1. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  2. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  3. 2023Cognitive Architectures for Language Agentscited by 422
  4. 2023Aligning Text-to-Image Models using Human Feedbackcited by 418
  5. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  6. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  7. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
  8. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  9. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
  10. 2016Cooperative Inverse Reinforcement Learningcited by 298
  11. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  12. 2020Consistent Estimators for Learning to Defer to an Expertcited by 262
  13. 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 245
  14. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 216
  15. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  16. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  17. 2023Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solvecited by 175
  18. 2022GitHub Copilot AI pair programmer: Asset or Liability?cited by 150
  19. 2023Getting aligned on representational alignmentcited by 142
  20. 2020Watch-And-Help: A Challenge for Social Perception and Human-AI Collaborationcited by 131
  21. 2022Automatic Generation of Programming Exercises and Code Explanations using Large Language Modelscited by 124
  22. 2020Reward-rational (implicit) choice: A unifying formalism for reward learningcited by 119
  23. 2021To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-makingcited by 118
  24. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 118
  25. 2023Calibrated Language Models Must Hallucinatecited by 114
  26. 2022Evaluating Human-Language Model Interactioncited by 90
  27. 2021Sparks: Inspiration for Science Writing using Language Modelscited by 80
  28. 2021Consequences of Misaligned AIcited by 79
  29. 2024Towards Conversational Diagnostic AIcited by 79
  30. 2023Evaluating Cognitive Maps and Planning in Large Language Models with CogEvalcited by 77
  31. 2024A Design Space for Intelligent and Interactive Writing Assistantscited by 76
  32. 2022Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writerscited by 69
  33. 2023Evaluating Language Models for Mathematics through Interactionscited by 69
  34. 2018A Review of Challenges and Opportunities in Machine Learning for Healthcited by 67
  35. 2020Online Bayesian Goal Inference for Boundedly-Rational Planning Agentscited by 67
  36. 2024Scaling Instructable Agents Across Many Simulated Worldscited by 67
  37. 2023Turning large language models into cognitive modelscited by 66
  38. 2021The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writerscited by 61

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 40; 2026: 25.

73 papers.

Sort:

By area:

  1. 2025Levels of Autonomy for AI Agentscited by 45
  2. 2024Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinkingcited by 43
  3. 2024Cocoa: Co-Planning and Co-Execution with AI Agentscited by 38
  4. 2024Can Large Language Models Understand Symbolic Graphics Programs?cited by 32
  5. 2025Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Modelscited by 28
  6. 2025On Benchmarking Human-Like Intelligence in Machinescited by 24
  7. 2025Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wildcited by 24
  8. 2025Assessing Adaptive World Models in Machines with Novel Gamescited by 20
  9. 2025Collaborating with AI Agents: Field Experiments on Teamwork, Productivity, and Performancecited by 14
  10. 2025Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Modelscited by 14
  11. 2024Imagining and building wise machines: The centrality of AI metacognitioncited by 12
  12. 2024Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learningcited by 11
38 more
  1. 2025Measuring and mitigating overreliance to build human-compatible AIcited by 9
  2. 2025When Should We Orchestrate Multiple Agents?cited by 7
  3. 2026AI Assistance Reduces Persistence and Hurts Independent Performancecited by 7
  4. 2026Computational Hermeneutics: Evaluating generative AI as a cultural technologycited by 7
  5. 2025Using LLMs to Advance the Cognitive Science of Collectivescited by 6
  6. 2025Revealing emergent human-like conceptual representations from language predictioncited by 5
  7. 2025Retrieval-augmented systems can be dangerous medical communicatorscited by 5
  8. 2025What's Producible May Not Be Reachable: Measuring the Steerability of Generative Modelscited by 5
  9. 2025AI shares emotion with humans across languages and culturescited by 5
  10. 2025Penalizing Transparency? How AI Disclosure and Author Demographics Shape Human and AI Judgments About Writingcited by 5
  11. 2024Multi-agent cooperation through learning-aware policy gradientscited by 4
  12. 2025Distributionally Robust Free Energy Principle for Decision-Makingcited by 4
  13. 2025A large-scale evaluation of commonsense knowledge in humans and large language modelscited by 4
  14. 2025Evaluating Language Models' Evaluations of Gamescited by 4
  15. 2025The Algorithmic State Architecture (ASA): An Integrated Framework for AI-Enabled Governmentcited by 3
  16. 2025Identifying, Evaluating, and Mitigating Risks of AI Thought Partnershipscited by 3
  17. 2025A Matter of Interest: Understanding Interestingness of Math Problems in Humans and Language Modelscited by 3
  18. 2025MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Imagescited by 3
  19. 2026Belief Offloading in Human-AI Interactioncited by 3
  20. 2026Why Human Guidance Matters in Collaborative Vibe Codingcited by 3
  21. 2026Overseeing Agents Without Constant Oversight: Challenges and Opportunitiescited by 3
  22. 2026Learning User Simulators with Turing Rewardscited by 3
  23. 2024Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Modelcited by 2
  24. 2025Revisiting Rogers' Paradox in the Context of Human-AI Interactioncited by 2
  25. 2025Documenting Deployment with Fabric: A Repository of Real-World AI Governancecited by 2
  26. 2025Estimating cognitive biases with attention-aware inverse planningcited by 2
  27. 2025Reliable agent engineering should integrate machine-compatible organizational principlescited by 2
  28. 2026AI as Entertainmentcited by 2
  29. 2026Under the Influence: Quantifying Persuasion and Vigilance in Large Language Modelscited by 2
  30. 2026Cognitive Models and AI Algorithms Provide Templates for Designing Language Agentscited by 2
  31. 2026Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impactcited by 2
  32. 2026Visuospatial Perspective Taking in Multimodal Language Modelscited by 2
  33. 2024Models Can and Should Embrace the Communicative Nature of Human-Generated Mathcited by 1
  34. 2025Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospectscited by 1
  35. 2025NiceWebRL: a Python library for human subject experiments with reinforcement learning environmentscited by 1
  36. 2025Language and Experience: A Computational Model of Social Learning in Complex Taskscited by 1
  37. 2025Uncovering the Computational Ingredients of Human-Like Representations in LLMscited by 1
  38. 2026Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learningcited by 1

50 most cited of 73 All 73 (JSON)