Introduces 'Umwelt Engineering,' the deliberate constraint of an agent's linguistic environment to improve reasoning.
March 31, 2026
Original Paper
Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents
arXiv · 2603.27626
The Takeaway
By removing basic words like 'to be' or 'to have,' the author forces models into a 'restructured' cognitive state that improves ethical reasoning and epistemic calibration. It suggests that agent performance can be optimized more effectively by changing the *medium* of thought rather than just the prompt or model scale.
From the 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