Componentization: Decomposing Monolithic LLM Responses into Manipulable Semantic Units
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912580411326464 |
|---|---|
| author | Lingo, Ryan Chhajer, Rajeev Arroyo, Martin Brkljacic, Luka Davis, Ben Santhanam, Nithin |
| author_facet | Lingo, Ryan Chhajer, Rajeev Arroyo, Martin Brkljacic, Luka Davis, Ben Santhanam, Nithin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08203 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Componentization: Decomposing Monolithic LLM Responses into Manipulable Semantic Units Lingo, Ryan Chhajer, Rajeev Arroyo, Martin Brkljacic, Luka Davis, Ben Santhanam, Nithin Human-Computer Interaction Artificial Intelligence Software Engineering I.2.7; H.5.2 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. |
| title | Componentization: Decomposing Monolithic LLM Responses into Manipulable Semantic Units |
| topic | Human-Computer Interaction Artificial Intelligence Software Engineering I.2.7; H.5.2 |
| url | https://arxiv.org/abs/2509.08203 |