mlsanityData to 7 Oct 2026

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

arXiv 2603.15690 ↗First posted 16 Mar 2026cs.SE cs.AIcited by 1

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

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: runtime generation and evolution under uncertainty. Drawing upon and extending software engineering experience, especially object-oriented programming, this paper introduces 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: View/Context Engineering to manage the execution environment and maintain task-relevant Views, Structure Engineering to organize dynamic binding over artifacts and agents, and 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 designability, scalability, and evolvability of agentic infrastructure. We provide basic experimental validation of key mechanisms, demonstrating the effectiveness of LSS.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 51 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

21 of 51 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023ChatDev: Communicative Agents for Software Development16 Jul

Other references · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2017Deep reinforcement learning from human preferencescited by 3,846
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  9. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  10. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  11. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  12. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
8 more
  1. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
  2. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 250
  3. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  4. 2025Towards a Science of Scaling Agent Systemscited by 125
  5. 2024What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineeringcited by 88
  6. 2026Agent Drift: Quantifying Behavioral Degradation in Multi-Agent LLM Systems Over Extended Interactionscited by 26
  7. 2025Defending against Indirect Prompt Injection by Instruction Detectioncited by 25
  8. 2024Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecturecited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Code Broker: A Multi-Agent System for Automated Code Quality Assessmentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities
  2. 2026Governed Evolution of Agent Runtimes through Executable Operational Cognition
  3. 2026Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
  4. 2025A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
  5. 2026Agentic Software: How AI Agents Are Restructuring the Software Paradigm
  6. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead
  7. 2026A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
  8. 2025Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale