Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents

Rodney Jehu-Appiah

Abstract

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.

Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents

Abstract

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.

Paper Structure

This paper contains 46 sections, 2 figures, 7 tables.

Table of Contents

  1. Introduction
  2. The Umwelt Concept
  3. The Three-Layer Stack
  4. Related Work
  5. Linguistic Relativity in LLMs
  6. Designed Reasoning Languages
  7. Beyond Linguistic Reasoning
  8. Cognitive Linguistics and AI
  9. E-Prime and General Semantics
  10. A Taxonomy of Linguistic Constraint Traditions
  11. Experiment 1: Linguistic Constraints as Cognitive Interventions
  12. Design
  13. Results
  14. Aggregate Accuracy
  15. Model-Specific Effects
  16. ...and 31 more sections

Figures (2)

  • Figure 1: The three-layer stack for AI agent design. Each layer is invisible from the one below it: a prompt engineer does not reason about the linguistic structures through which prompts are interpreted. Umwelt engineering operates on the vocabulary, grammar, and conceptual primitives that constitute the agent's cognitive world.
  • Figure 2: Crossover pattern of constraint effects across seven reasoning tasks (all models pooled). No-Have (orange) shows a more uniformly positive profile. E-Prime (blue) improves causal and ethical reasoning while degrading syllogisms and epistemic calibration. Tasks ordered by No-Have effect size.