# Componentization: Decomposing Monolithic LLM Responses into Manipulable Semantic Units

arXiv: https://arxiv.org/abs/2509.08203 · HTML: https://mlsanity.com/paper/2509.08203/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [Beyond the Chat: Executable and Verifiable Text-Editing with LLMs](https://mlsanity.com/paper/2309.15337/) (2023)
- [Flow: Modularized Agentic Workflow Automation](https://mlsanity.com/paper/2501.07834/) (2025)
- [IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking](https://mlsanity.com/paper/2410.07295/) (2024)
- [AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation](https://mlsanity.com/paper/2504.07532/) (2025)
- [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://mlsanity.com/paper/2505.16023/) (2025)
- [CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming](https://mlsanity.com/paper/2310.09235/) (2023)
- [PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation](https://mlsanity.com/paper/2409.12538/) (2024)
- [Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process](https://mlsanity.com/paper/2504.12488/) (2025)
- [Low-code LLM: Graphical User Interface over Large Language Models](https://mlsanity.com/paper/2304.08103/) (2023)
- [Prompting Generative AI with Interaction-Augmented Instructions](https://mlsanity.com/paper/2503.02874/) (2025)
- [Human-Centered LLM-Agent User Interface: A Position Paper](https://mlsanity.com/paper/2405.13050/) (2024)
- [Integrating Large Language Models into Text Animation: An Intelligent Editing System with Inline and Chat Interaction](https://mlsanity.com/paper/2506.10762/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) often produce monolithic text that is hard to edit in parts, which can slow down collaborative workflows. We present componentization, an approach that decomposes model outputs into modular, independently editable units while preserving context. We describe Modular and Adaptable Output Decomposition (MAOD), which segments responses into coherent components and maintains links among them, and we outline the Component-Based Response Architecture (CBRA) as one way to implement this idea. Our reference prototype, MAODchat, uses a microservices design with state-machine-based decomposition agents, vendor-agnostic model adapters, and real-time component manipulation with recomposition. In an exploratory study with four participants from academic, engineering, and product roles, we observed that component-level editing aligned with several common workflows and enabled iterative refinement and selective reuse. Participants also mentioned possible team workflows. Our contributions are: (1) a definition of componentization for transforming monolithic outputs into manipulable units, (2) CBRA and MAODchat as a prototype architecture, (3) preliminary observations from a small user study, (4) MAOD as an algorithmic sketch for semantic segmentation, and (5) example Agent-to-Agent protocols for automated decomposition. We view componentization as a promising direction for turning passive text consumption into more active, component-level collaboration.