Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Bo Pan, Lunke Pan, Yitao Zhou, Qi Jiang, Zhen Wen, Minfeng Zhu, Wei Chen

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.

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

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.
Paper Structure (35 sections, 3 equations, 5 figures)

This paper contains 35 sections, 3 equations, 5 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Deep Research Systems
  4. Interface for Information Seeking
  5. Formative Study
  6. Participants and Procedure
  7. Findings
  8. Design Goals
  9. Research Context Management
  10. Hierarchical Research Context Architecture
  11. Level1: Research Information
  12. Level2: Research Action
  13. Level3: Research Session
  14. Research Context Reduction
  15. Research Context Backtrace
  16. ...and 20 more sections

Figures (5)

  • Figure 1: The hierarchical research context architecture across three levels: information, actions, and sessions.
  • Figure 2: InterDeepResearch interface with three coordinated views: (A) chat-style view for research sessions and research action flow, (B) graph-based view for research action dependencies, and (C) card-style view for detailed research information.
  • Figure 3: The cross-action backtrace mechanism helps users trace the provenance of generated content.
  • Figure 4: InterDeepResearch achieves competitive performance on existing text-based deep research benchmarks.
  • Figure 5: The results of the questionnaire regarding our system’s effectiveness and usability.