Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search

Kyle A. McCleary, James M. Ghawaly


Abstract
Agentic Retrieval-Augmented Generation (RAG) systems combine iterative search, planning prompts, and retrieval backends, but deployed settings impose explicit budgets on tool calls and completion tokens. We present a controlled measurement study of how search depth, retrieval strategy, and completion budget affect accuracy and cost under fixed constraints. Using Budget-Constrained Agentic Search (BCAS), a model-agnostic evaluation harness that surfaces remaining budget and gates tool use, we run comparisons across six LLMs and three question-answering benchmarks. Across models and datasets, accuracy improves with additional searches up to a small cap, hybrid lexical and dense retrieval with lightweight re-ranking produces the largest average gains in our ablation grid, and larger completion budgets are most helpful on HotpotQA-style synthesis. These results provide practical guidance for configuring budgeted agentic retrieval pipelines and are accompanied by reproducible prompts and evaluation settings.
Anthology ID:
2026.lrec-1.808
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
10291–10300
Language:
External URL:
https://lrec.elra.info/lrec2026-main-808
DOI:
10.63317/3wfsiry9yjog
Bibkey:
Cite (ACL):
Kyle A. McCleary and James M. Ghawaly. 2026. Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 10291–10300, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search (McCleary & Ghawaly, LREC 2026)
Copy Citation: