Tenure Two · 2026–2027

Viveka 2.0

Interpreting and advancing ARC-AGI 2 — probing the limits of abstract reasoning, compositional generalisation, and genuine novelty-handling in frontier AI systems.

Focus AreaAGI Evaluation & Reasoning
DurationAug 2026 – May 2027
Researchers9 Members
StatusUpcoming
01 — Technical Introduction

Can AI systems truly reason about novel problems?

ARC-AGI 2 represents one of the most demanding evaluations of abstract reasoning in AI: tasks designed explicitly so that memorisation and pattern-matching are insufficient. Success requires genuine compositional generalisation — the ability to combine known primitives in ways never encountered during training.

Meet the Viveka 2.0 Team

3 project leads and 6 researchers tackling abstract reasoning and AGI evaluation through 2026–27.

View Team →
03 — Recruitment

Recruitment Starting Soon

Applications for Viveka 2.0 will open shortly. Stay tuned for details on how to join the team for the 2026–2027 tenure.