Tag
This paper introduces a category-aware expert training framework for software engineering agents to mitigate uneven progress across task categories, using iterative training and multi-teacher distillation, with significant performance gains on Pro-618 and SWE-bench Multilingual benchmarks.
HyPE introduces a hypergraph-based persona encoder that models high-order relations among persona attributes via category-aware hyperedges and persistent edge embeddings, achieving consistent improvements over flat pooling baselines on PersonaChat across multiple backbone models.