Context Matters: Evaluating Context Strategies for Automated ADR Generation Using LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gupta, Aviral, Dhar, Rudra, Feitosa, Daniel, Vaidhyanathan, Karthik
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918448088481792
author Gupta, Aviral
Dhar, Rudra
Feitosa, Daniel
Vaidhyanathan, Karthik
author_facet Gupta, Aviral
Dhar, Rudra
Feitosa, Daniel
Vaidhyanathan, Karthik
contents Architecture Decision Records (ADRs) play a critical role in preserving the rationale behind system design, yet their creation and maintenance are often neglected due to the associated authoring overhead. This paper investigates whether Large Language Models (LLMs) can mitigate this burden and, more importantly, how different strategies for presenting historical ADRs as context influence generation quality. We curate and validate a large corpus of sequential ADRs drawn from 750 open-source repositories and systematically evaluate five context selection strategies (no context, All-history, First-K, Last-K, and RAFG) across multiple model families. Our results show that context-aware prompting substantially improves ADR generation fidelity, with a small recency window (typically 3-5 prior records) providing the best balance between quality and efficiency. Retrieval-based context selection yields marginal gains primarily in non-sequential or cross-cutting decision scenarios, while offering no statistically significant advantage in typical linear ADR workflows. Overall, our findings demonstrate that context engineering, rather than model scale alone, is the dominant factor in effective ADR automation, and we outline practical defaults for tool builders along with targeted retrieval fallbacks for complex architectural settings.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03826
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Context Matters: Evaluating Context Strategies for Automated ADR Generation Using LLMs
Gupta, Aviral
Dhar, Rudra
Feitosa, Daniel
Vaidhyanathan, Karthik
Software Engineering
Architecture Decision Records (ADRs) play a critical role in preserving the rationale behind system design, yet their creation and maintenance are often neglected due to the associated authoring overhead. This paper investigates whether Large Language Models (LLMs) can mitigate this burden and, more importantly, how different strategies for presenting historical ADRs as context influence generation quality. We curate and validate a large corpus of sequential ADRs drawn from 750 open-source repositories and systematically evaluate five context selection strategies (no context, All-history, First-K, Last-K, and RAFG) across multiple model families. Our results show that context-aware prompting substantially improves ADR generation fidelity, with a small recency window (typically 3-5 prior records) providing the best balance between quality and efficiency. Retrieval-based context selection yields marginal gains primarily in non-sequential or cross-cutting decision scenarios, while offering no statistically significant advantage in typical linear ADR workflows. Overall, our findings demonstrate that context engineering, rather than model scale alone, is the dominant factor in effective ADR automation, and we outline practical defaults for tool builders along with targeted retrieval fallbacks for complex architectural settings.
title Context Matters: Evaluating Context Strategies for Automated ADR Generation Using LLMs
topic Software Engineering
url https://arxiv.org/abs/2604.03826