Paper Detail
Zhiyuan Wang, Erzhen Hu, Mark Rucker, Laura E. Barnes
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{wang2026psi,
title = {PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents},
author = {Zhiyuan Wang and Erzhen Hu and Mark Rucker and Laura E. Barnes},
year = {2026},
abstract = {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 acros},
url = {https://arxiv.org/abs/2604.08529},
keywords = {cs.HC, cs.AI, Affordance, Computer science, Layer (electronics), State (computer science), Software deployment},
eprint = {2604.08529},
archiveprefix = {arXiv},
}
{}