Exploring Information Seeking Agent Consolidation
Abstract
Information-seeking agents have emerged as a powerful paradigm for solving knowledge-intensive tasks. Existing information-seeking agents are typically specialized for open web, documents, or local knowledge bases, which constrains scalability and cross-domain generalization. In this work, we investigate how to consolidate heterogeneous information-seeking agents into a single foundation agentic model. We study two complementary consolidation strategies: data-level consolidation, which jointly trains a unified model on a mixture of domain-specific datasets, and parameter-level consolidation, which merges independently trained agent models at the parameter level. Our analysis compares these approaches in terms of performance retention, cross-domain generalization, and interference across information-seeking behaviors. Our results show that data-level consolidation remains a strong and stable baseline, while parameter-level consolidation offers a promising, efficient alternative but suffers from interference and robustness challenges. We further identify key design factors for effective agent consolidation at the parameter level, including fine-grained merging granularity, awareness of task heterogeneity, and principled consensus strategy.
Cite
@article{arxiv.2602.00585,
title = {Exploring Information Seeking Agent Consolidation},
author = {Guochen Yan and Jialong Wu and Zhengwei Tao and Bo Li and Qintong Zhang and Jiahao Xu and Haitao Mi and Yuejian Fang and Qingni Shen and Wentao Zhang and Zhonghai Wu},
journal= {arXiv preprint arXiv:2602.00585},
year = {2026}
}