H2R uses hierarchical hints as rewards for math reasoning
Qwen2.5-Math-7B rises from 30.4% to 39.1% on HiMath with hierarchical hints, and to 45.6% with oracle hints.
Stories per day · 30 days
3 RSS
2 stories, newest first · one card per story
Stories tagged #reward-design
Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
Researchers propose Feedback-Enriched Environments (FEEs) that reduce reward sparsity and improve RL training of Qwen3-based agents on SciWorld and BFCL.