IDRBench: Interactive Deep Research Benchmark

ACL ARR 2026 January Submission6373 Authors

Keywords: Interactive Deep Research, Human-AI Interaction, Evaluation Benchmark, LLM Agents

Abstract: Deep research agents powered by Large Language Models (LLMs) can perform multi-step reasoning, web exploration, and long-form report generation. However, most existing systems operate in an *autonomous* manner, assuming fully specified user intent and evaluating only final outputs. In practice, research goals are often underspecified and evolve during exploration, making sustained interaction essential for robust alignment. Despite its importance, interaction remains largely invisible to existing deep research benchmarks, which neither model dynamic user feedback nor quantify its costs. We introduce **IDRBench**, the first benchmark for systematically evaluating *interactive* deep research. IDRBench combines a modular multi-agent research framework with on-demand interaction, a scalable reference-grounded user simulator, and an interaction-aware evaluation suite that jointly measures interaction benefits (quality and alignment) and costs (turns and tokens). Experiments across seven state-of-the-art LLMs show that interaction consistently improves research quality and robustness, often outweighing differences in model capacity, while revealing substantial trade-offs in interaction efficiency. The source code is available at \url{https://anonymous.4open.science/r/IDRBench-F650}.

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: Resources and Evaluation,Human-AI Interaction/Cooperation and Human-Centric NLP,AI/LLM Agents,Retrieval-Augmented Language Models

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 6373