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

2026-03-12

AI Summary

This work proposes an interactive deep research system that enables human-AI collaboration, addressing the limitations of conventional “query-to-report” paradigms wherein users passively receive results without the ability to intervene or incorporate personal knowledge. The system introduces a novel hierarchical research context management architecture comprising information, action, and conversation layers, supporting dynamic context compression and cross-action backtracking. Coupled with a tri-view collaborative visualization interface, it renders the research process observable, steerable, and efficiently navigable. Built upon large language model agents and integrating an evidence-provenance mechanism, the system achieves state-of-the-art performance on the Xbench-DeepSearch-v1 and Seal-0 benchmarks. User studies demonstrate its significant improvement in collaborative information-seeking efficiency and user experience.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Intelligent User Interfaces

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• human-agent collaboration
• interactive deep research
• information seeking
• research context management
• LLM agents

Innovation

• human-agent collaboration
• interactive deep research
• context management framework
• hierarchical context architecture
• evidence provenance