Deep Cognition: A Transparent, Fine-Grained Multi-Agent Deep Research System for Human-Agent Collaboration

ACL ARR 2026 January Submission8683 Authors

Keywords: Human Agent Interaction, Deep Research System

Abstract: As AI systems engage in extended thinking processes for research tasks, interaction becomes increasingly important for effective long-horizon research. In these tasks, many current deep research systems still follow an ``input–wait–output” paradigm: users submit a query and receive results only after a non-interruptible process with limited visibility into intermediate decisions. In multi-agent systems, delayed feedback can amplify early errors, limit query refinement during investigation and reduce opportunities for expertise integration. To address these limitations, we introduce Deep Cognition, a multi-agent deep research system that enables users to monitor and steer an ongoing research process through targeted interventions during execution. Deep Cognition provides two key capabilities: (1)Transparent, controllable, and interruptible interaction that reveals AI reasoning, exposing intermediate plans and evidence and allowing users to intervene at intermediate checkpoints; (2)Fine-grained bidirectional dialogue that enables per-subagent control during execution. User evaluation demonstrates that deep cognition outperforms the strong 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\%) and yields a 45.45\%–72.73\% improvement in benchmark evaluation.

Paper Type: Long

Research Area: Human-AI Interaction/Cooperation and Human-Centric NLP

Research Area Keywords: Dialogue and Interactive Systems, Human-Centered NLP, Interpretability and Analysis of Models for NLP

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 8683