SOURCE-LINKED INTELLIGENCE

Aspire: Can Models Self-Evolve from Vague Goals?

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved. In contrast, existing work on LLM self-evolution typically begins with tasks and evaluation metrics specified by humans, reducing self-evolution to optimizing an explicit objective rather than deciding what and how to learn. We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution. ASPIRE provides only a natural-language capabi

Read original source ↗ Open in workspace

recordType

paper

region

Global