Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents
For LLM practitioners, this work introduces a new method to improve reasoning and ensemble diversity by constraining the language models use, though results are preliminary and lack an active control.
Umwelt engineering—deliberately altering the linguistic cognitive environment—improves LLM reasoning: No-Have constraints boost ethical reasoning by 19.1 pp and classification by 6.5 pp, while a 3-agent ensemble with diverse constraints achieves 100% ground-truth coverage on debugging problems vs. 88.2% for the control.
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.