SOURCE-LINKED INTELLIGENCE

HISPO: Hierarchical Importance-Sampling Policy Optimization with Entropy-Derived Segments

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Reinforcement learning with verifiable rewards (RLVR) has become a central approach for improving mathematical reasoning in language models, but long-form completions introduce a difficult credit-assignment problem: different parts of a solution trace may contribute unevenly to final correctness. Existing policyoptimization objectives for RLVR commonly apply importance-sampling correction at either the token level (GRPO, DAPO) or the sequence level (GSPO), imposing different granularities for assigning credit across a response. We introduce Hierarchical Importance-Sampling Policy Optimization

Read original source ↗ Open in workspace

recordType

paper

region

Global