BRAID: Bounded Reasoning for Autonomous Inference and Decisions

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Amcalar, Armağan, Cinar, Eyup
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911325318283264
author Amcalar, Armağan
Cinar, Eyup
author_facet Amcalar, Armağan
Cinar, Eyup
contents Large Language Models (LLMs) exhibit nonlinear relationships between performance, cost, and token usage. This paper presents a quantitative study on structured prompting using BRAID (Bounded Reasoning for Au tonomous Inference and Decisions) across multiple GPT model tiers, eval uated on the AdvancedIF, GSM-Hard, and the SCALE MultiChallenge benchmark datasets. BRAID introduces a bounded reasoning framework using Mermaid-based instruction graphs that enable models to reason struc turally rather than through unbounded natural-language token expansion. We show that structured machine-readable prompts substantially increase reasoning accuracy and cost efficiency for agents in production systems. The findings establish BRAID as an effective and scalable technique for optimizing inference efficiency in autonomous agent systems. All datasets and detailed result logs are available at https://benchmark.openserv.ai.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15959
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BRAID: Bounded Reasoning for Autonomous Inference and Decisions
Amcalar, Armağan
Cinar, Eyup
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) exhibit nonlinear relationships between performance, cost, and token usage. This paper presents a quantitative study on structured prompting using BRAID (Bounded Reasoning for Au tonomous Inference and Decisions) across multiple GPT model tiers, eval uated on the AdvancedIF, GSM-Hard, and the SCALE MultiChallenge benchmark datasets. BRAID introduces a bounded reasoning framework using Mermaid-based instruction graphs that enable models to reason struc turally rather than through unbounded natural-language token expansion. We show that structured machine-readable prompts substantially increase reasoning accuracy and cost efficiency for agents in production systems. The findings establish BRAID as an effective and scalable technique for optimizing inference efficiency in autonomous agent systems. All datasets and detailed result logs are available at https://benchmark.openserv.ai.
title BRAID: Bounded Reasoning for Autonomous Inference and Decisions
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2512.15959