mlsanityData to 14 Oct 2026

The Cartesian Cut in Agentic AI

arXiv 2604.07745 ↗First posted 9 Apr 2026cs.AI q-bio.NCcited by 0

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

Abstract (arXiv)

LLMs gain competence by predicting words in human text, which often reflects how people perform tasks. Consequently, coupling an LLM to an engineered runtime turns prediction into control: outputs trigger interventions that enact goal-oriented behavior. We argue that a central design lever is where control resides in these systems. Brains embed prediction within layered feedback controllers calibrated by the consequences of action. By contrast, LLM agents implement Cartesian agency: a learned core coupled to an engineered runtime via a symbolic interface that externalizes control state and policies. The split enables bootstrapping, modularity, and governance, but can induce sensitivity and bottlenecks. We outline bounded services, Cartesian agents, and integrated agents as contrasting approaches to control that trade off autonomy, robustness, and oversight.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 30 of its 71 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

30 of 71 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022A Generalist Agent12 May

Other references · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  7. 2017Deep reinforcement learning from human preferencescited by 3,912
  8. 2023Let's Verify Step by Stepcited by 3,789
  9. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  10. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  11. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  12. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
17 more
  1. 2022Emergent Abilities of Large Language Modelscited by 2,512
  2. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  3. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  5. 2016Concrete Problems in AI Safetycited by 1,642
  6. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  7. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  8. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  9. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  10. 2020Mastering Atari with Discrete World Modelscited by 1,007
  11. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  12. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 809
  13. 2022PAL: Program-aided Language Modelscited by 652
  14. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  15. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  16. 2024Alignment faking in large language modelscited by 360
  17. 2025Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?cited by 75

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026The Path Ahead for Agentic AI: Challenges and Opportunities
  2. 2025What Do LLM Agents Do When Left Alone? Evidence of Spontaneous Meta-Cognitive Patterns
  3. 2026Active Inference: A method for Phenotyping Agency in AI systems?
  4. 2026From Task Solving to Robust Real-World Adaptation in LLM Agents
  5. 2026Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts
  6. 2026Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents
  7. 2026From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments
  8. 2026Critique of Agent Model