mlsanityData to 14 Oct 2026

PSI: Shared State as the Missing Layer for Coherent AI-Generated Instruments in Personal AI Agents

arXiv 2604.08529 ↗First posted 9 Apr 2026cs.HC cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 9 of its 40 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

9 of 40 references.

References · 9

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  4. 2023Graphologue: Exploring Large Language Model Responses with Interactive Diagramscited by 66
  5. 2023Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creationcited by 64
  6. 2025Creating General User Models from Computer Usecited by 44
  7. 2024DynaVis: Dynamically Synthesized UI Widgets for Visualization Editingcited by 37
  8. 2025Generative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Modelcited by 26
  9. 2024OmniActions: Predicting Digital Actions in Response to Real-World Multimodal Sensory Inputs with LLMscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.