Beyond the Prompt: Assessing Domain Knowledge Strategies for High-Dimensional LLM Optimization in Software Engineering
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910009759105024 |
|---|---|
| author | Srinivasan, Srinath Menzies, Tim |
| author_facet | Srinivasan, Srinath Menzies, Tim |
| contents | Background/Context: Large Language Models (LLMs) demonstrate strong performance on low-dimensional software engineering optimization tasks ($\le$11 features) but consistently underperform on high-dimensional problems where Bayesian methods dominate. A fundamental gap exists in understanding how systematic integration of domain knowledge (whether from humans or automated reasoning) can bridge this divide.
Objective/Aim: We compare human versus artificial intelligence strategies for generating domain knowledge. We systematically evaluate four distinct architectures to determine if structured knowledge integration enables LLMs to generate effective warm starts for high-dimensional optimization.
Method: We evaluate four approaches on MOOT datasets stratified by dimensionality: (1) Human-in-the-Loop Domain Knowledge Prompting (H-DKP), utilizing asynchronous expert feedback loops; (2) Adaptive Multi-Stage Prompting (AMP), implementing sequential constraint identification and validation; (3) Dimension-Aware Progressive Refinement (DAPR), conducting optimization in progressively expanding feature subspaces; and (4) Hybrid Knowledge-Model Approach (HKMA), synthesizing statistical scouting (TPE) with RAG-enhanced prompting. Performance is quantified via Chebyshev distance to optimal solutions and ranked using Scott-Knott clustering against an established baseline for LLM generated warm starts.
Note that all human studies conducted as part of this study will comply with the policies of our local Institutional Review Board. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02752 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond the Prompt: Assessing Domain Knowledge Strategies for High-Dimensional LLM Optimization in Software Engineering Srinivasan, Srinath Menzies, Tim Software Engineering Background/Context: Large Language Models (LLMs) demonstrate strong performance on low-dimensional software engineering optimization tasks ($\le$11 features) but consistently underperform on high-dimensional problems where Bayesian methods dominate. A fundamental gap exists in understanding how systematic integration of domain knowledge (whether from humans or automated reasoning) can bridge this divide. Objective/Aim: We compare human versus artificial intelligence strategies for generating domain knowledge. We systematically evaluate four distinct architectures to determine if structured knowledge integration enables LLMs to generate effective warm starts for high-dimensional optimization. Method: We evaluate four approaches on MOOT datasets stratified by dimensionality: (1) Human-in-the-Loop Domain Knowledge Prompting (H-DKP), utilizing asynchronous expert feedback loops; (2) Adaptive Multi-Stage Prompting (AMP), implementing sequential constraint identification and validation; (3) Dimension-Aware Progressive Refinement (DAPR), conducting optimization in progressively expanding feature subspaces; and (4) Hybrid Knowledge-Model Approach (HKMA), synthesizing statistical scouting (TPE) with RAG-enhanced prompting. Performance is quantified via Chebyshev distance to optimal solutions and ranked using Scott-Knott clustering against an established baseline for LLM generated warm starts. Note that all human studies conducted as part of this study will comply with the policies of our local Institutional Review Board. |
| title | Beyond the Prompt: Assessing Domain Knowledge Strategies for High-Dimensional LLM Optimization in Software Engineering |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2602.02752 |