Skip to content
#generative ai Open access

Theoretical Engineering

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

This paper introduces Theoretical Engineering, a framework that systematically applies engineering management (version control, exception handling) and design (interface layering, decoupling) to theoretical construction and thinking management, with the ultimate goal of achieving recursive automation of theoretical inquiry. As an initial exploration, this work focuses on defining high-level architecture and core interface protocols. The fundamental operational unit is the "abstract interface." A central diagnosis identifies the common pathology underlying numerous philosophical and scientific deadlocks: protocol mismatch—applying static, bounded protocols to dynamic, recursively generative processes. The prescribed remedy emphasizes interface reconstruction and graceful degradation/caching rather than outright deletion. Driving these operations is the Dimension-Free Updatism (DFU) engine, which elevates Bayesian updating from parameter adjustment to structural transitions in rule space ("wall-breaking"), unifying decoupling across data, strategy, and architecture layers. A complete theory, within this view, comprises orthogonal and independently consumable intuitive and formalized coding layers. The framework delivers systematic resolutions across multiple domains: Cognition: Distinguishes static from dynamic reasoning to dissolve Hume's induction problem, mapping the historical evolution of cognition (intuition → dogma → positivism → Popper → Bayesian → DFU). Consciousness: Redefines consciousness as a recursive "perceive-comprehend-react" operation, with experience defined as its persistable output data, systematically addressing zombies, the Chinese Room, and the explanatory gap. Ethics: Formalizes value as Bayesian posterior probability, meaning as prior, and existence/survival as the normalization constant, with morality defined as group-imposed behavioral constraints based on high-value actions, bridging the is-ought gap and extending to AI alignment and multi-agent system sustainability. Paradoxes: Proposes a unified "straight-line (infinite recursion) vs. line-segment (bounded)" model to reduce Russell's, Liar, Curry, Zeno's, Gettier, and other self-referential or semantic paradoxes to a single structural violation. At the meta-level, the paper introduces "Recursive Nested Philosophy" to replace ambiguous "meta-" terminology, emphasizing the input-output relay between inner and outer layers. This paper does not claim a complete implementation but offers a scalable top-level interface signature for future computational and engineering development. All assertions herein are declared relative truths, explicitly subject to revision upon future empirical or formal evidence. 本文提出理论工程学(Theoretical Engineering),旨在将工程管理(版本控制、异常处理)与工程设计(接口分层、解耦)方法系统引入理论构建与思维管理,目标指向理论研究的递归自动化。这是对该框架的初步探索,侧重于顶层架构设计与核心接口协议的定义。 核心路径:以“抽象接口”为基本操作单元,诊断哲学与科学理论中大量困境的共性病因——协议错配(用静态实体的判定协议处理动态递归的生成过程)。处理策略为“接口重构”与“降级/缓存”,而非删除异常。底层以维度自由更新论(DFU)驱动,将贝叶斯更新从参数层升维至规则空间的结构跃迁层,统一数据、决策与结构的解耦。 主要消解与重构成果: 认知层:将推理区分为“静态推理”与“动态推理”,消解休谟归纳问题,并构建认知操作谱系(直觉→教条→实证→波普尔→贝叶斯→DFU)。 意识层:将意识重构为“感知-理解-反应”的循环递归操作,体验界定为其输出的可持久化数据,系统回应了哲学僵尸、中文房间、解释鸿沟等核心意识难题。 伦理层:将价值映射为贝叶斯后验概率,意义映射为先验,存续映射为归一化常数,道德界定为群体基于高价值量的行为约束规范,打通休谟实然-应然鸿沟,并延伸至AI安全与多智能体存续。 悖论统一层:以“直线(无限递归)与线段(有限边界)”单一模型,统一归约罗素悖论、说谎者悖论、柯里悖论、芝诺悖论、盖梯尔问题等所有自指及语义困境。 元层定位:提出“递归嵌套哲学”替代“元哲学”术语,强调内外层输入输出的承接关系。本文不声称全貌实现,而是提供可扩展的顶层接口签名;所有断言声明为相对真理,主动接受后续证据检验。 Feel free to discuss with me by following email 欢迎通过以下邮箱与我讨论: zl.chen.research@outlook.com

View source

Similar papers

#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations

Related blog posts

GPT-Lab Sep 17, 2026

Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering

AI is making software generation faster, but speed does not remove the need for expertise. As more work is delegated to AI, tacit knowledge may become one of the most important human advantages in software engineering. The post Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering appeared first on GPT-Lab.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.