multi-domain-reasoning

Tag

Cards List
#multi-domain-reasoning

Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR

Hugging Face Daily Papers · 2026-06-27 Cached

This paper proposes Transfer-Aware Curriculum (TAC), a bandit-style online curriculum for multi-domain RLVR that prioritizes domains whose updates benefit other domains using gradient-geometry alignment. TAC improves macro-averaged accuracy on Qwen3-1.7B and Llama3.2-3B over fixed and learnability-only curricula.

0 favorites 0 likes
← Back to home

Submit Feedback