Enhancing Intelligence Through the Suppression of Other Intelligence: A General Framework
Abstract
Intelligence is commonly enhanced by improving existing capabilities, adding resources, acquiring knowledge, or increasing computational power. However, another possibility deserves systematic investigation: suppressing some intelligent components may improve the performance of other components or the overall intelligent system. This paper proposes a general framework for studying this possibility. The framework applies not only to large language models (LLMs), neural networks, and multi-agent systems, but also to other systems in which intelligent components, processes, or behaviors can be identified and evaluated.
Suppression may involve reducing the activity, influence, participation, communication, or operational priority of a selected component. Its purpose is not necessarily to eliminate that component permanently, but to reduce its contribution when that contribution interferes with a target capability or system objective. The resulting improvement may arise from reduced interference, released computational resources, better coordination, or changes in the relationships between components. This paper defines the central concepts, presents a simple mathematical formulation, identifies potential mechanisms, and proposes a practical evaluation method. The framework does not assume that suppression always improves intelligence. Instead, it establishes a research question: under what conditions can selectively suppressing one part of an intelligent system enhance another part or improve the system as a whole?
Related
- Enhancing Intelligence Through the Suppression of Other Intelligence: A General Framework for Multi-Agent Systems
- Enhancing Large Language Models Through the Suppression of Other Intelligence: A General Framework
- Deletion Learning for Multi-Agent Systems (DL-MAS): A General Framework for Enhancing Collective Intelligence Through Pre-Training, In-Training, and Post-Training Deletion
- Deletion Learning (DL): A General Framework for Enhancing Learning Systems Through Pre-Learning, In-Learning, and Post-Learning Deletion
- Zero-Onboard-AI-Compute Embodied Intelligence: A General Framework for Collective Computing Through Idle Resources of Other Embodied Agents
BibTeX
@misc{zhang2026enhancing,
title = {{Enhancing Intelligence Through the Suppression of Other Intelligence: A General Framework}},
author = {Jincheng Zhang},
howpublished = {Zenodo},
year = {2026},
month = oct,
doi = {10.5281/zenodo.23469109},
url = {https://zenodo.org/records/23469109},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Enhancing Intelligence Through the Suppression of Other Intelligence: A General Framework
AU - Jincheng Zhang
PY - 2026
DA - 2026/10/19
PB - Zenodo
DO - 10.5281/zenodo.23469109
UR - https://zenodo.org/records/23469109
AB - Intelligence is commonly enhanced by improving existing capabilities, adding resources, acquiring knowledge, or increasing computational power. However, another possibility deserves systematic investigation: suppressing some intelligent components may improve the performance of other components or the overall intelligent system. This paper proposes a general framework for studying this possibility. The framework applies not only to large language models (LLMs), neural networks, and multi-agent systems, but also to other systems in which intelligent components, processes, or behaviors can be identified and evaluated. Suppression may involve reducing the activity, influence, participation, communication, or operational priority of a selected component. Its purpose is not necessarily to eliminate that component permanently, but to reduce its contribution when that contribution interferes with a target capability or system objective. The resulting improvement may arise from reduced interference, released computational resources, better coordination, or changes in the relationships between components. This paper defines the central concepts, presents a simple mathematical formulation, identifies potential mechanisms, and proposes a practical evaluation method. The framework does not assume that suppression always improves intelligence. Instead, it establishes a research question: under what conditions can selectively suppressing one part of an intelligent system enhance another part or improve the system as a whole?
ER -