Human Tool: An MCP-Style Framework for Human-Agent Collaboration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912903176650752 |
|---|---|
| author | Tang, Yuanrong Peng, Huiling Zhao, Bingxi Ding, Hengyang Song, Hanchao Wang, Tianhong Zhong, Chen Gong, Jiangtao |
| author_facet | Tang, Yuanrong Peng, Huiling Zhao, Bingxi Ding, Hengyang Song, Hanchao Wang, Tianhong Zhong, Chen Gong, Jiangtao |
| contents | Human-AI collaboration faces growing challenges as AI systems increasingly outperform humans on complex tasks, while humans remain responsible for orchestration, validation, and decision oversight. To address this imbalance, we introduce Human Tool, an MCP-style interface abstraction, building on recent Model Context Protocol designs, that exposes humans as callable tools within AI-led, proactive workflows. Here, "tool" denotes a coordination abstraction, not a reduction of human authority or responsibility. Building on LLM-based agent architectures, we operationalize Human Tool by modeling human contributions through structured tool schemas of capabilities, information, and authority. These schemas enable agents to dynamically invoke human input based on relative strengths and reintegrate it through efficient, natural interaction protocols. We validate the framework through controlled studies in both decision-making and creative tasks, demonstrating improved task performance, reduced human workload, and more balanced collaboration dynamics compared to baseline systems. Finally, we discuss implications for human-centered AI design, highlighting how MCP-style human tools enable strong AI leadership while amplifying uniquely human strengths. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12953 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Human Tool: An MCP-Style Framework for Human-Agent Collaboration Tang, Yuanrong Peng, Huiling Zhao, Bingxi Ding, Hengyang Song, Hanchao Wang, Tianhong Zhong, Chen Gong, Jiangtao Human-Computer Interaction 68U35 H.1.2 Human-AI collaboration faces growing challenges as AI systems increasingly outperform humans on complex tasks, while humans remain responsible for orchestration, validation, and decision oversight. To address this imbalance, we introduce Human Tool, an MCP-style interface abstraction, building on recent Model Context Protocol designs, that exposes humans as callable tools within AI-led, proactive workflows. Here, "tool" denotes a coordination abstraction, not a reduction of human authority or responsibility. Building on LLM-based agent architectures, we operationalize Human Tool by modeling human contributions through structured tool schemas of capabilities, information, and authority. These schemas enable agents to dynamically invoke human input based on relative strengths and reintegrate it through efficient, natural interaction protocols. We validate the framework through controlled studies in both decision-making and creative tasks, demonstrating improved task performance, reduced human workload, and more balanced collaboration dynamics compared to baseline systems. Finally, we discuss implications for human-centered AI design, highlighting how MCP-style human tools enable strong AI leadership while amplifying uniquely human strengths. |
| title | Human Tool: An MCP-Style Framework for Human-Agent Collaboration |
| topic | Human-Computer Interaction 68U35 H.1.2 |
| url | https://arxiv.org/abs/2602.12953 |