Social OMNI-EPIC: Learning-Progress-Driven Curriculum Generation for Social Interaction
Huijun Mao ⋅ Huanxing Chen ⋅ Nick Haber
Abstract
To address the rapid saturation of fixed social benchmarks by increasingly capable models, we introduce Social OMNI-EPIC, an open-ended curriculum generation framework that adapts learning-progress-driven environment design to LLM-based social simulation. Starting from a seed archive, it continuously generates scenarios targeting a learner's evolving capability frontier using intrinsic signals of learning progress and interestingness. Across 90 generated scenarios, Social OMNI-EPIC shifts the distribution from predominantly easy scenarios toward frontier-level challenges and becomes increasingly calibrated over time.
Chat is not available.
Successful Page Load