Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.08529 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913019476312064 |
|---|---|
| author | Wang, Zhiyuan Hu, Erzhen Rucker, Mark Barnes, Laura E. |
| author_facet | Wang, Zhiyuan Hu, Erzhen Rucker, Mark Barnes, Laura E. |
| contents | Personal AI tools can now be generated from natural-language requests, but they often remain isolated after creation. We present PSI, a shared-state architecture that turns independently generated modules into coherent instruments: persistent, connected, and chat-complementary artifacts accessible through both GUIs and a generic chat agent. By publishing current state and write-back affordances to a shared personal-context bus, modules enable cross-module reasoning and synchronized actions across interfaces. We study PSI through a three-week autobiographical deployment in a self-developed personal AI environment and show that later-generated instruments can be integrated automatically through the same contract. PSI identifies shared state as the missing systems layer that transforms AI-generated personal software from isolated apps into coherent personal computing environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08529 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents Wang, Zhiyuan Hu, Erzhen Rucker, Mark Barnes, Laura E. Human-Computer Interaction Artificial Intelligence Personal AI tools can now be generated from natural-language requests, but they often remain isolated after creation. We present PSI, a shared-state architecture that turns independently generated modules into coherent instruments: persistent, connected, and chat-complementary artifacts accessible through both GUIs and a generic chat agent. By publishing current state and write-back affordances to a shared personal-context bus, modules enable cross-module reasoning and synchronized actions across interfaces. We study PSI through a three-week autobiographical deployment in a self-developed personal AI environment and show that later-generated instruments can be integrated automatically through the same contract. PSI identifies shared state as the missing systems layer that transforms AI-generated personal software from isolated apps into coherent personal computing environments. |
| title | PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2604.08529 |