# Texas Tech researchers test reliability-aware tool retrieval for agents > RATED combines semantic matching with feedback on whether tools work during execution. - Canonical URL: https://newsverum.com/en/news/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval - Publisher: Newsverum - Section: Technology - Country: United States - Published: 2026-10-13T00:51:41+00:00 - Updated: 2026-10-13T00:51:41+00:00 - Event / data period: 2026-10-09 - Other editions: [Türkçe](https://newsverum.com/tr/news/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval.md), [العربية](https://newsverum.com/ar/news/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval.md), [Français](https://newsverum.com/fr/news/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval.md), [Español](https://newsverum.com/es/news/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval.md), [Deutsch](https://newsverum.com/de/news/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval.md), [Português](https://newsverum.com/pt/news/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval.md) Texas Tech University researchers introduced RATED, a method that ranks agent tools using both query relevance and execution feedback. It pairs a semantic encoder with a contextual bandit that reorders tools after success or failure signals. On the EcoAgent benchmark, the authors report a 52.2% relative MRR gain over the ToolLLM API retriever. In a simulated outage affecting 30% of tools, the rate of selecting failed tools fell from 86.2% for that baseline to 2.9% with RATED. These are benchmark-query and injected-failure results; they do not establish reliability in production. ## Data ### Measure EcoAgent real-query evaluation; compared with ToolLLM API Retriever Methodology: Values come from the paper's stated benchmark experiments; they are not field measurements or general performance guarantees. | Measure | Reported value | Experimental scope | |---|---|---| | RATED: relative MRR gain | 52.2 | EcoAgent real-query evaluation; compared with ToolLLM API Retriever | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval/data/result-1?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval/data/result-1?lang=en&format=csv) ### Measure EcoAgent simulated outage experiment; share of tools Methodology: Values come from the paper's stated benchmark experiments; they are not field measurements or general performance guarantees. | Measure | Reported value | Experimental scope | |---|---|---| | Share of tools with injected outages | 30 | EcoAgent simulated outage experiment; share of tools | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval/data/result-2?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval/data/result-2?lang=en&format=csv) ### Measure ToolLLM API Retriever in the same simulated outage test Methodology: Values come from the paper's stated benchmark experiments; they are not field measurements or general performance guarantees. | Measure | Reported value | Experimental scope | |---|---|---| | Failed-tool selection with ToolLLM API Retriever | 86.2 | ToolLLM API Retriever in the same simulated outage test | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval/data/result-3?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval/data/result-3?lang=en&format=csv) ### Measure RATED in the same simulated outage test Methodology: Values come from the paper's stated benchmark experiments; they are not field measurements or general performance guarantees. | Measure | Reported value | Experimental scope | |---|---|---| | Failed-tool selection with RATED | 2.9 | RATED in the same simulated outage test | Sources: · Download data: [JSON](https://newsverum.com/api/v1/articles/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval/data/result-4?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/texas-tech-study-adds-runtime-reliability-to-ai-tool-retrieval/data/result-4?lang=en&format=csv) ## Sources - [arXiv preprint by Texas Tech University researchers]() (Source checked: 2026-10-13; Published: 2026-10-09) --- Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)