Interaction as Intelligence: Deep Research With Human-AI Partnership
🤖 AI Summary
Traditional deep research systems reduce human-AI interaction to unidirectional capability invocation, leading to error cascades, rigid problem formulation, and poor integration of domain expertise. To address these limitations, we propose the “Interaction-as-Intelligence” paradigm, wherein dynamic, bidirectional human-AI collaboration serves as the core mechanism for intelligent reasoning. Our approach introduces a cognitive supervision framework that enables transparent and controllable AI inference, fine-grained two-way dialogue, and shared cognitive context. We further design three key components: interruptible interaction protocols, real-time feedback-driven dialogue, and behavior-adaptive models—collectively forming a hybrid cognitive architecture. Experiments demonstrate consistent improvements over the strongest baseline: +8.8%–29.2% across six core metrics, and +31.8%–50.0% on complex research tasks. The framework significantly enhances problem evolution capability and domain knowledge integration efficacy.
Application Category
📝 Abstract
This paper introduces "Interaction as Intelligence" research series, presenting a reconceptualization of human-AI relationships in deep research tasks. Traditional approaches treat interaction merely as an interface for accessing AI capabilities-a conduit between human intent and machine output. We propose that interaction itself constitutes a fundamental dimension of intelligence. As AI systems engage in extended thinking processes for research tasks, meaningful interaction transitions from an optional enhancement to an essential component of effective intelligence. Current deep research systems adopt an "input-wait-output" paradigm where users initiate queries and receive results after black-box processing. This approach leads to error cascade effects, inflexible research boundaries that prevent question refinement during investigation, and missed opportunities for expertise integration. To address these limitations, we introduce Deep Cognition, a system that transforms the human role from giving instructions to cognitive oversight-a mode of engagement where humans guide AI thinking processes through strategic intervention at critical junctures. Deep cognition implements three key innovations: (1)Transparent, controllable, and interruptible interaction that reveals AI reasoning and enables intervention at any point; (2)Fine-grained bidirectional dialogue; and (3)Shared cognitive context where the system observes and adapts to user behaviors without explicit instruction. User evaluation demonstrates that this cognitive oversight paradigm outperforms the strongest baseline across six key metrics: Transparency(+20.0%), Fine-Grained Interaction(+29.2%), Real-Time Intervention(+18.5%), Ease of Collaboration(+27.7%), Results-Worth-Effort(+8.8%), and Interruptibility(+20.7%). Evaluations on challenging research problems show 31.8% to 50.0% points of improvements over deep research systems.
Problem
Research questions and friction points this paper is trying to address.
Reconceptualizing human-AI interaction as fundamental intelligence in research
Addressing error cascades and inflexibility in traditional input-wait-output AI systems
Enabling real-time human oversight through transparent, interruptible AI reasoning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Transparent, controllable, interruptible AI interaction
Fine-grained bidirectional dialogue system
Shared cognitive context adaptation
🔎 Similar Papers
No similar papers found.
