Research & Writing

The science of learning individuals.

Explore our research, open initiatives, and writing on how AI can continuously learn about individuals and adapt to them.

Four research directions, one field: learning individuals.

01Research directions

Four questions at the core of individual learning.

How can AI understand an individual deeply enough to adapt meaningfully—while learning efficiently, recognizing uncertainty, and improving through experience?

01

Efficient Individual Learning

How can AI learn a new individual from limited evidence? What should it ask next, and how can active elicitation improve understanding per interaction?

02

Conditional & Uncertainty-Aware Modeling

How can AI distinguish stable individual tendencies from domain-specific preferences, temporary circumstances, and unknown or conflicting evidence?

03

Cross-Domain Preference Learning

What knowledge transfers between different contexts, and how can AI identify when transfer is useful—or likely to be misleading?

04

Closed-Loop Adaptation & Evaluation

How can predictions, targeted verification, and feedback improve user-specific decisions and interaction policies over time?

02Open research community

Learning to Work with You

An open research agenda and community for User-Specific Interaction Learning (USIL).

How should AI agents learn when to ask, act, explain, or return control—adapting how they work with each person through experience?

Learning to Work with You brings together research questions at the intersection of agent learning, human–AI interaction, personalization, and robotics.

We’re building an open community where researchers and practitioners can explore shared problems, contribute to a living research map, develop evaluation approaches, and collaborate on new ideas.

Learning to Work with You: AI should learn to work with you.

Explore the agenda

Explore the open research agenda and the living research map.

Contribute

Contribute papers, corrections, and research questions.

Collaborate

Connect with researchers and explore collaborations.

Idios Labs explores individual learning broadly. Learning to Work with You focuses specifically on user-specific interaction learning, as an open scientific community.

03Evaluation & benchmarks

How quickly can AI learn an individual?

Ongoing research direction · Individual Learning Benchmark

Given limited interactions with an individual, how accurately can a system predict their preferences and desired AI behavior on unseen tasks and domains?

This work is in progress. We plan to share methodology and results as they mature.

We are developing an evaluation framework that examines:

  • Prediction accuracyGeneralization to unseen tasks and domains.
  • Question efficiencyUseful understanding gained per interaction.
  • CalibrationWhether uncertainty estimates match observed performance.
  • Negative transferWhen applying knowledge across domains causes errors.
  • Downstream adaptationWhether AI requires fewer corrections and better meets individual needs.

04Writing

Ideas and perspectives