# Interaction as Intelligence: Deep Research With Human-AI Partnership

arXiv: https://arxiv.org/abs/2507.15759 · HTML: https://mlsanity.com/paper/2507.15759/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 76 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [In-context Reinforcement Learning with Algorithm Distillation](https://mlsanity.com/paper/2210.14215/) (2022)
- [MiniMax-01: Scaling Foundation Models with Lightning Attention](https://mlsanity.com/paper/2501.08313/) (2025)
- [Measuring AI Ability to Complete Long Software Tasks](https://mlsanity.com/paper/2503.14499/) (2025)
- [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025)
- [Supervised Pretraining Can Learn In-Context Reinforcement Learning](https://mlsanity.com/paper/2306.14892/) (2023)
- [Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining](https://mlsanity.com/paper/2310.08566/) (2023)
- [Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation](https://mlsanity.com/paper/2310.12953/) (2023)
- ["Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction](https://mlsanity.com/paper/2210.03735/) (2022)
- [Mechanistic Design and Scaling of Hybrid Architectures](https://mlsanity.com/paper/2403.17844/) (2024)
- [In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making](https://mlsanity.com/paper/2305.07722/) (2023)
- [Levels of Autonomy for AI Agents](https://mlsanity.com/paper/2506.12469/) (2025)
- [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://mlsanity.com/paper/2408.15232/) (2024)
- [Need Help? Designing Proactive AI Assistants for Programming](https://mlsanity.com/paper/2410.04596/) (2024)
- [Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce](https://mlsanity.com/paper/2506.06576/) (2025)
- [Proactive Conversational Agents with Inner Thoughts](https://mlsanity.com/paper/2501.00383/) (2024)
- [RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents](https://mlsanity.com/paper/2506.00618/) (2025)
- [CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent](https://mlsanity.com/paper/2310.06155/) (2023)
- [Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support](https://mlsanity.com/paper/2502.18658/) (2025)
- [Generative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Model](https://mlsanity.com/paper/2503.04084/) (2025)
- [DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning](https://mlsanity.com/paper/2505.24332/) (2025)
- [Human-AI collaboration is not very collaborative yet: A taxonomy of interaction patterns in AI-assisted decision making from a systematic review](https://mlsanity.com/paper/2310.19778/) (2023)
- [Advancing the Search Frontier with AI Agents](https://mlsanity.com/paper/2311.01235/) (2023)
- [AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses](https://mlsanity.com/paper/2501.16240/) (2025)

## Built on by (most cited first, 5 of 5)

- [InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research](https://mlsanity.com/paper/2510.27598/) (2025)
- [Context Engineering 2.0: The Context of Context Engineering](https://mlsanity.com/paper/2510.26493/) (2025)
- [DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces](https://mlsanity.com/paper/2509.13444/) (2025)
- [IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning](https://mlsanity.com/paper/2602.03468/) (2026)
- [Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training](https://mlsanity.com/paper/2510.27630/) (2025)

## Abstract (arXiv)

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.