Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.16997 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914166165471232 |
|---|---|
| author | Zeng, Qingbin Fan, Bingbing Chen, Zhiyu Ren, Sijian Zhou, Zhilun Zhang, Xuhua Zhen, Yuanyi Xu, Fengli Li, Yong Liu, Tie-Yan |
| author_facet | Zeng, Qingbin Fan, Bingbing Chen, Zhiyu Ren, Sijian Zhou, Zhilun Zhang, Xuhua Zhen, Yuanyi Xu, Fengli Li, Yong Liu, Tie-Yan |
| contents | The emergence of AI Scientists has demonstrated remarkable potential in automating scientific research. However, current approaches largely conceptualize scientific discovery as a solitary optimization or search process, overlooking that knowledge production is inherently a social and historical endeavor. Human scientific insight stems from two distinct yet interconnected sources. First is the individual cognitive trajectory, where a researcher's unique insight is shaped by their evolving research history and stylistic preferences; another is the collective disciplinary memory, where knowledge is sedimented into vast, interconnected networks of citations and concepts. Existing LLMs still struggle to represent these structured, high-fidelity cognitive and social contexts. To bridge this gap, we introduce MirrorMind, a hierarchical cognitive architecture that integrates dual-memory representations within a three-level framework. The Individual Level constructs high-fidelity cognitive models of individual researchers by capturing their episodic, semantic, and persona memories; the Domain Level maps collective knowledge into structured disciplinary concept graphs; and the Interdisciplinary Level that acts as an orthogonal orchestration engine. Crucially, our architecture separates memory storage from agentic execution, enabling AI scientist agents to flexibly access individual memories for unique perspectives or collective structures to reason. We evaluate MirrorMind across four comprehensive tasks, including author-level cognitive simulation, complementary reasoning, cross-disciplinary collaboration promotion, and multi-agent scientific problem solving. The results show that by integrating individual cognitive depth with collective disciplinary breadth, MirrorMind moves beyond simple fact retrieval toward structural, personalized, and insight-generating scientific reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16997 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientists Zeng, Qingbin Fan, Bingbing Chen, Zhiyu Ren, Sijian Zhou, Zhilun Zhang, Xuhua Zhen, Yuanyi Xu, Fengli Li, Yong Liu, Tie-Yan Artificial Intelligence The emergence of AI Scientists has demonstrated remarkable potential in automating scientific research. However, current approaches largely conceptualize scientific discovery as a solitary optimization or search process, overlooking that knowledge production is inherently a social and historical endeavor. Human scientific insight stems from two distinct yet interconnected sources. First is the individual cognitive trajectory, where a researcher's unique insight is shaped by their evolving research history and stylistic preferences; another is the collective disciplinary memory, where knowledge is sedimented into vast, interconnected networks of citations and concepts. Existing LLMs still struggle to represent these structured, high-fidelity cognitive and social contexts. To bridge this gap, we introduce MirrorMind, a hierarchical cognitive architecture that integrates dual-memory representations within a three-level framework. The Individual Level constructs high-fidelity cognitive models of individual researchers by capturing their episodic, semantic, and persona memories; the Domain Level maps collective knowledge into structured disciplinary concept graphs; and the Interdisciplinary Level that acts as an orthogonal orchestration engine. Crucially, our architecture separates memory storage from agentic execution, enabling AI scientist agents to flexibly access individual memories for unique perspectives or collective structures to reason. We evaluate MirrorMind across four comprehensive tasks, including author-level cognitive simulation, complementary reasoning, cross-disciplinary collaboration promotion, and multi-agent scientific problem solving. The results show that by integrating individual cognitive depth with collective disciplinary breadth, MirrorMind moves beyond simple fact retrieval toward structural, personalized, and insight-generating scientific reasoning. |
| title | MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientists |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2511.16997 |