Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.19298 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913708324683776 |
|---|---|
| author | Kanoulas, Evangelos Eustratiadis, Panagiotis Li, Yongkang Lyu, Yougang Pal, Vaishali Poerwawinata, Gabrielle Qiao, Jingfen Wang, Zihan |
| author_facet | Kanoulas, Evangelos Eustratiadis, Panagiotis Li, Yongkang Lyu, Yougang Pal, Vaishali Poerwawinata, Gabrielle Qiao, Jingfen Wang, Zihan |
| contents | As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domains. In such a system, answering a query requires selecting a small subset of relevant models, querying them efficiently, and synthesizing their responses. This paper introduces a framework for agent-centric information access, where LLMs function as knowledge agents that are dynamically ranked and queried based on their demonstrated expertise. Unlike traditional document retrieval, this approach requires inferring expertise on the fly, rather than relying on static metadata or predefined model descriptions. This shift introduces several challenges, including efficient expert selection, cost-effective querying, response aggregation across multiple models, and robustness against adversarial manipulation. To address these issues, we propose a scalable evaluation framework that leverages retrieval-augmented generation and clustering techniques to construct and assess thousands of specialized models, with the potential to scale toward millions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19298 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Agent-centric Information Access Kanoulas, Evangelos Eustratiadis, Panagiotis Li, Yongkang Lyu, Yougang Pal, Vaishali Poerwawinata, Gabrielle Qiao, Jingfen Wang, Zihan Information Retrieval As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domains. In such a system, answering a query requires selecting a small subset of relevant models, querying them efficiently, and synthesizing their responses. This paper introduces a framework for agent-centric information access, where LLMs function as knowledge agents that are dynamically ranked and queried based on their demonstrated expertise. Unlike traditional document retrieval, this approach requires inferring expertise on the fly, rather than relying on static metadata or predefined model descriptions. This shift introduces several challenges, including efficient expert selection, cost-effective querying, response aggregation across multiple models, and robustness against adversarial manipulation. To address these issues, we propose a scalable evaluation framework that leverages retrieval-augmented generation and clustering techniques to construct and assess thousands of specialized models, with the potential to scale toward millions. |
| title | Agent-centric Information Access |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2502.19298 |