Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.15759 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911067855126528 |
|---|---|
| author | Ye, Lyumanshan Cai, Xiaojie Wang, Xinkai Wang, Junfei Hu, Xiangkun Su, Jiadi Nan, Yang Wang, Sihan Zhang, Bohan Fan, Xiaoze Luo, Jinbin Zheng, Yuxiang Xu, Tianze Fu, Dayuan Wu, Yunze Lu, Pengrui Wang, Zengzhi Qin, Yiwei Huang, Zhen Ma, Yan Hu, Zhulin Zou, Haoyang Mi, Tiantian Ye, Yixin Chern, Ethan Liu, Pengfei |
| author_facet | Ye, Lyumanshan Cai, Xiaojie Wang, Xinkai Wang, Junfei Hu, Xiangkun Su, Jiadi Nan, Yang Wang, Sihan Zhang, Bohan Fan, Xiaoze Luo, Jinbin Zheng, Yuxiang Xu, Tianze Fu, Dayuan Wu, Yunze Lu, Pengrui Wang, Zengzhi Qin, Yiwei Huang, Zhen Ma, Yan Hu, Zhulin Zou, Haoyang Mi, Tiantian Ye, Yixin Chern, Ethan Liu, Pengfei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15759 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interaction as Intelligence: Deep Research With Human-AI Partnership Ye, Lyumanshan Cai, Xiaojie Wang, Xinkai Wang, Junfei Hu, Xiangkun Su, Jiadi Nan, Yang Wang, Sihan Zhang, Bohan Fan, Xiaoze Luo, Jinbin Zheng, Yuxiang Xu, Tianze Fu, Dayuan Wu, Yunze Lu, Pengrui Wang, Zengzhi Qin, Yiwei Huang, Zhen Ma, Yan Hu, Zhulin Zou, Haoyang Mi, Tiantian Ye, Yixin Chern, Ethan Liu, Pengfei Computation and Language 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. |
| title | Interaction as Intelligence: Deep Research With Human-AI Partnership |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.15759 |