Exploring Information Seeking Agent Consolidation

TL;DR

This paper investigates methods to unify diverse information-seeking agents into a single model, comparing data-level and parameter-level consolidation strategies for improved scalability and cross-domain generalization.

Contribution

It introduces and evaluates two consolidation strategies, providing insights into their performance, challenges, and key design considerations for creating a unified agent model.

Findings

Data-level consolidation is a stable baseline.

Parameter-level consolidation faces interference issues.

Key design factors include merging granularity and task awareness.

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.