DataFunSummit

Jul 9, 2026 · Artificial Intelligence

Token-Level Credit Assignment Outperforms Broadcast GRPO in LLM Math Reasoning

The paper identifies the broadcast‑style credit assignment of GRPO as a bottleneck for RL‑LLM math reasoning, proposes the Outcome‑Grounded Advantage Reshaping (OAR) framework with token‑importance estimation, and demonstrates that its two variants, OAR‑P and OAR‑G, consistently improve accuracy, training efficiency, and stability across multiple math benchmarks.