Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.19566 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911173081825280 |
|---|---|
| author | Hong, George Banos, Daniel Trejo |
| author_facet | Hong, George Banos, Daniel Trejo |
| contents | We investigate the application of Small Language Models (<10 billion parameters) for genomics question answering via agentic framework to address hallucination issues and computational cost challenges. The Nano Bio-Agent (NBA) framework we implemented incorporates task decomposition, tool orchestration, and API access into well-established systems such as NCBI and AlphaGenome. Results show that SLMs combined with such agentic framework can achieve comparable and in many cases superior performance versus existing approaches utilising larger models, with our best model-agent combination achieving 98% accuracy on the GeneTuring benchmark. Notably, small 3-10B parameter models consistently achieve 85-97% accuracy while requiring much lower computational resources than conventional approaches. This demonstrates promising potential for efficiency gains, cost savings, and democratization of ML-powered genomics tools while retaining highly robust and accurate performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19566 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Nano Bio-Agents (NBA): Small Language Model Agents for Genomics Hong, George Banos, Daniel Trejo Artificial Intelligence Genomics We investigate the application of Small Language Models (<10 billion parameters) for genomics question answering via agentic framework to address hallucination issues and computational cost challenges. The Nano Bio-Agent (NBA) framework we implemented incorporates task decomposition, tool orchestration, and API access into well-established systems such as NCBI and AlphaGenome. Results show that SLMs combined with such agentic framework can achieve comparable and in many cases superior performance versus existing approaches utilising larger models, with our best model-agent combination achieving 98% accuracy on the GeneTuring benchmark. Notably, small 3-10B parameter models consistently achieve 85-97% accuracy while requiring much lower computational resources than conventional approaches. This demonstrates promising potential for efficiency gains, cost savings, and democratization of ML-powered genomics tools while retaining highly robust and accurate performance. |
| title | Nano Bio-Agents (NBA): Small Language Model Agents for Genomics |
| topic | Artificial Intelligence Genomics |
| url | https://arxiv.org/abs/2509.19566 |