All papersReasoning & AgentsTrendingTop pick on Nov 9Oxford

From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence

/ Paper arXiv 2611.05376

Curator's notes

The paper proposes AI-augmented human intelligence via lifelong, private cognitive symbionts that assist people in real time.

Curator's notesWritten by AI from the paperReport a mistake

What's new

It shifts focus from autonomous AI to AI that continuously augments an individual’s cognition, defining a symbiosis loopsymbiosis loopThe design cycle of sensing, keeping, understanding, living alongside, acting for, thinking with, and growing with the user. and governance considerations.

Why it matters

Developers can build systems that extend human memory and decision‑making, creating more effective personal assistants.

Abstract

From the paperThe authors' own words.

For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own. Large foundation models now write code and run multistep tasks, and personal agents act on a person's behalf. Yet people still forget what they once knew, miss what they are not looking at, fail to find the right words, and face hard choices without the benefit of their own history, because the machine that could help stands outside the situation. As AI moves into the physical world, attention has settled on one kind of intelligent individual, the embodied robot; we argue that the era of Physical AI holds a second kind of equal importance, the person augmented by AI. Alongside artificial general intelligence, which asks how intelligent a machine can be, stands AI-augmented human intelligence (AHI), which asks how much intelligence a machine can enable in a particular person. Realizing it calls for a new kind of system, a cognitive symbiontcognitive symbiontA lifelong, embedded AI companion that continuously assists and learns from a specific person.: a lifelong, embedded, real-time, private, low-friction, and proactive companion that senses what the person senses through external devices, keeps their context across years, models their situation and their mind, takes part in their thinking at the right moment, carries out everyday tasks with their context, and keeps learning the person as both change. We give the paradigm a conceptual core, the cognitive gapcognitive gapThe difference between what a person can bring to a situation and what they can hold in working memory. between what a person could bring to a situation and what they can hold in working memory, and organize its design space as a symbiosis loop of sensing, keeping, understanding, living alongside, acting for and thinking with the person, and growing, enclosed by a personal runtime and by trust. Because a symbiont changes what a person can do in front of others, it also raises risks of a new kind, from covert assistance in examinations to pressure on everyone to adopt it, and we treat their governance as part of the paradigm.

From the full paper

From the paperCopied from the paper itself by our code.

Reading the paper on arXiv…

What you could build

Written by AIAdvancedRequires lifelong data integration, privacy safeguards, and real‑time multimodal sensing.

  1. Create a context‑aware note‑taking assistant that updates with personal history.
  2. Develop a proactive task manager that suggests actions based on sensed environment.
  3. Build a privacy‑preserving personal AI that models user preferences over years.

Ask this paper

/ Ask a questionAnswers come from the full paper and name the section

    / Quiz yourself

    What core concept does the paper introduce to bridge the gap between a person’s situational knowledge and their working memory?

    / Your notes

    Select text in the abstract to highlight it or add a note. They stay in this browser.

      / Next pickEvoMemState: Evolving Memory State for Personal Agents
      Read the PDF