InterDeepResearch: Enabling Human-Agent Collaborative Information Seeking through Interactive Deep Research

TL;DR

InterDeepResearch introduces an interactive system that enhances human-agent collaboration in deep research by organizing research context hierarchically, enabling real-time steerability and efficient context management, supported by a user-friendly interface.

Contribution

The paper presents a novel interactive deep research system with a hierarchical context management framework that improves collaboration, context navigation, and process observability in human-agent research workflows.

Findings

Achieves competitive performance on benchmark datasets.

Demonstrates improved human-agent collaboration in user studies.

Provides effective context management and navigation mechanisms.

Abstract

Deep research systems powered by LLM agents have transformed complex information seeking by automating the iterative retrieval, filtering, and synthesis of insights from massive-scale web sources. However, existing systems predominantly follow an autonomous "query-to-report" paradigm, limiting users to a passive role and failing to integrate their personal insights, contextual knowledge, and evolving research intents. This paper addresses the lack of human-in-the-loop collaboration in the agentic research process. Through a formative study, we identify that current systems hinder effective human-agent collaboration in terms of process observability, real-time steerability, and context navigation efficiency. Informed by these findings, we propose InterDeepResearch, an interactive deep research system backed by a dedicated research context management framework. The framework organizes research context into a hierarchical architecture with three levels (information, actions, and sessions), enabling dynamic context reduction to prevent LLM context exhaustion and cross-action backtracing for evidence provenance. Built upon this framework, the system interface integrates three coordinated views for visual sensemaking, and dedicated interaction mechanisms for interactive research context navigation. Evaluation on the Xbench-DeepSearch-v1 and Seal-0 benchmarks shows that InterDeepResearch achieves competitive performance compared to state-of-the-art deep research systems, while a formal user study demonstrates its effectiveness in supporting human-agent collaborative information seeking. Project page with system demo: https://github.com/bopan3/InterDeepResearch.