Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems

Weihao Zhang, Yitong Zhou, Huanyu Qu, Hongyi Li

Abstract

As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling the number of agents often amplifies context pressure, coordination errors, and system drift. It is well known that building robust MAS requires more than prompt tuning or increased model intelligence. It necessitates engineering discipline focused on architecture to manage complexity under uncertainty. We characterize agentic software by a core property: \emph{runtime generation and evolution under uncertainty}. Drawing upon and extending software engineering experience, especially object-oriented programming, this paper introduces \emph{Loosely-Structured Software (LSS)}, a new class of software systems that shifts the engineering focus from constructing deterministic logic to managing the runtime entropy generated by View-constructed programming, semantic-driven self-organization, and endogenous evolution. To make this entropy governable, we introduce design principles under a three-layer engineering framework: \emph{View/Context Engineering} to manage the execution environment and maintain task-relevant Views, \emph{Structure Engineering} to organize dynamic binding over artifacts and agents, and \emph{Evolution Engineering} to govern the lifecycle of self-rewriting artifacts. Building on this framework, we develop LSS design patterns as semantic control blocks that stabilize fluid, inference-mediated interactions while preserving agent adaptability. Together, these abstractions improve the \emph{designability}, \emph{scalability}, and \emph{evolvability} of agentic infrastructure. We provide basic experimental validation of key mechanisms, demonstrating the effectiveness of LSS.

Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems

Abstract

As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling the number of agents often amplifies context pressure, coordination errors, and system drift. It is well known that building robust MAS requires more than prompt tuning or increased model intelligence. It necessitates engineering discipline focused on architecture to manage complexity under uncertainty. We characterize agentic software by a core property: \emph{runtime generation and evolution under uncertainty}. Drawing upon and extending software engineering experience, especially object-oriented programming, this paper introduces \emph{Loosely-Structured Software (LSS)}, a new class of software systems that shifts the engineering focus from constructing deterministic logic to managing the runtime entropy generated by View-constructed programming, semantic-driven self-organization, and endogenous evolution. To make this entropy governable, we introduce design principles under a three-layer engineering framework: \emph{View/Context Engineering} to manage the execution environment and maintain task-relevant Views, \emph{Structure Engineering} to organize dynamic binding over artifacts and agents, and \emph{Evolution Engineering} to govern the lifecycle of self-rewriting artifacts. Building on this framework, we develop LSS design patterns as semantic control blocks that stabilize fluid, inference-mediated interactions while preserving agent adaptability. Together, these abstractions improve the \emph{designability}, \emph{scalability}, and \emph{evolvability} of agentic infrastructure. We provide basic experimental validation of key mechanisms, demonstrating the effectiveness of LSS.
Paper Structure (22 sections, 2 equations, 16 figures)

This paper contains 22 sections, 2 equations, 16 figures.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Basic Concepts of Multi-Agent Systems
  4. Related Work
  5. Definition of Loosely-Structured Software
  6. Conceptual Features
  7. System Model: Runtime Elements and Primitives
  8. View/Context Engineering: Taming Context Entropy
  9. Design Principles
  10. Design Patterns
  11. Structure Engineering: Taming Self-Organization Entropy
  12. Design Principles
  13. Design Patterns
  14. Evolution Engineering: Taming Evolutionary Entropy
  15. Design Principles
  16. ...and 7 more sections

Figures (16)

  • Figure 1: The engineering focus shifts from designing specific logical code to designing runtime generation and evolution.
  • Figure 2: Loosely-Structured Software: a software system with unstable, runtime-generated structure & abstraction and its dominant engineering focuses (View, Binding, Evolution).
  • Figure 3: Comparison of Architectural Paradigms: Traditional Software vs. LSS. Left: Traditional software relies on compile-time program structure to constrain runtime behavior. Right: LSS makes behavior depend on the runtime trajectory of Views and Artifacts, which induces the effective agent configuration over time.
  • Figure 4: Multi-agent interaction in LSS, represented using UML-style sequence diagram notation. The diagram illustrates how the primitives decompose the loosely-structured runtime.
  • Figure 5: Three-layer engineering framework for LSS: View--Context, Structure--Capability, and Evolution--Adaptation.
  • ...and 11 more figures