# Trust by Design: Skill Profiles for Transparent, Cost-Aware LLM Routing

arXiv: https://arxiv.org/abs/2602.02386 · HTML: https://mlsanity.com/paper/2602.02386/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [GraphRouter: A Graph-based Router for LLM Selections](https://mlsanity.com/paper/2410.03834/) (2024)
- [EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees](https://mlsanity.com/paper/2503.08893/) (2025)
- [Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models](https://mlsanity.com/paper/2410.13826/) (2024)

## Built on by (most cited first, 2 of 2)

- [Explainable Model Routing for Agentic Workflows](https://mlsanity.com/paper/2604.03527/) (2026)
- [RouteProfile: Graph-Based Profiling for Cold-Start LLM Routing](https://mlsanity.com/paper/2605.00180/) (2026)

## Abstract (arXiv)

How should Large Language Model (LLM) practitioners select the right model for a task without wasting money? We introduce BELLA (Budget-Efficient LLM Selection via Automated skill-profiling), a framework that recommends optimal LLM selection for tasks through interpretable skill-based model selection. Standard benchmarks report aggregate metrics that obscure which specific capabilities a task requires and whether a cheaper model could suffice. BELLA addresses this gap through three stages: (1) decomposing LLM outputs and extract the granular skills required by using critic-based profiling, (2) clustering skills into structured capability matrices, and (3) multi-objective optimization to select the right models to maximize performance while respecting budget constraints. BELLA provides natural-language rationale for recommendations, providing transparency that current black-box routing systems lack. We describe the framework architecture, situate it within the landscape of LLM routing and evaluation, and discuss its application to financial reasoning as a representative domain exhibiting diverse skill requirements and cost-variation across models. Our framework enables practitioners to make principled and cost-performance trade-offs for deploying LLMs.