mlsanityData to 7 Oct 2026

Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents

arXiv 2603.27626 ↗First posted 29 Mar 2026cs.CL cs.AIcited by 1

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

Abstract (arXiv)

I propose Umwelt engineering -- the deliberate design of the linguistic cognitive environment -- as a third layer in the agent design stack, upstream of both prompt and context engineering. Two experiments test the thesis that altering the medium of reasoning alters cognition itself. In Experiment 1, three language models reason under two vocabulary constraints -- No-Have (eliminating possessive "to have") and E-Prime (eliminating "to be") -- across seven tasks (N=4,470 trials). No-Have improves ethical reasoning by 19.1 pp (p < 0.001), classification by 6.5 pp (p < 0.001), and epistemic calibration by 7.4 pp, while achieving 92.8% constraint compliance. E-Prime shows dramatic but model-dependent effects: cross-model correlations reach r = -0.75. In Experiment 2, 16 linguistically constrained agents tackle 17 debugging problems. No constrained agent outperforms the control individually, yet a 3-agent ensemble achieves 100% ground-truth coverage versus 88.2% for the control. A permutation test confirms only 8% of random 3-agent subsets achieve full coverage, and every successful subset contains the counterfactual agent. Two mechanisms emerge: cognitive restructuring and cognitive diversification. The primary limitation is the absence of an active control matching constraint prompt elaborateness.

Key facts. Cited by 1 paper 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 6 of its 16 references that are in the map. First posted on arXiv 29 Mar 2026.

Builds on

6 of 16 references.

References · 6

  1. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  2. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 292
  3. 2024Does Prompt Formatting Have Any Impact on LLM Performance?cited by 132
  4. 2025From Language to Cognition: How LLMs Outgrow the Human Language Networkcited by 30
  5. 2025Conceptual Metaphor Theory as a Prompting Paradigm for Large Language Modelscited by 3
  6. 2025Under the Shadow of Babel: How Language Shapes Reasoning in LLMscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraintscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents
  2. 2025Towards Cognitive Synergy in LLM-Based Multi-Agent Systems: Integrating Theory of Mind and Critical Evaluation
  3. 2023Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning
  4. 2025The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
  5. 2024Towards Rationality in Language and Multimodal Agents: A Survey
  6. 2025United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory
  7. 2024MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset
  8. 2025Unified Mind Model: Reimagining Autonomous Agents in the LLM Era