cs.CLNov 10, 2026

Are Dense Rewards Worth Their Tokens in GRPO?

Authors: Vikash Singh, Weicong Chen, Debargha Ganguly, Yanyan Zhang, Mohsen Hariri, Sreehari Sankar, Wang Yang, Chaoda Song, 

Organizations: Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, OH, USA.

Abstract

RLVR trains language models to reason by rewarding correct final answers. A widely used algorithm, group-relative policy optimization (GRPO), gives every token of a solution the same credit, so dense process rewards have been proposed to credit intermediate steps, for example with a Monte-Carlo reward that scores each step by sampling continuations from it. Comparing such a reward with GRPO per training update, or vetting it with a gradient test on a single batch, leaves out what it costs: in our setting, the continuations alone take 91% of all generated tokens. We introduce a matched-compute protocol that gives every training intervention the same budget, measured in generated tokens and training GPU-hours, and tests it in preregistered studies with controls for side effects. Across 1,668 runs on six models, matching compute reverses the ranking. On Qwen2.5-1.5B, the Monte-Carlo reward leads standard GRPO per update, yet ends 14.3 percentage points lower at equal tokens and 7.8 points lower at equal training time, and none of four dense-reward variants outperforms GRPO even with as much training time. A per-token gradient test orders these rewards as training does but overestimates each by one to two points, as much as the gains it is meant to detect. In contrast, training on the prompts whose predicted success is nearest 1/2 improves accuracy at matched compute, by 1.7 points on Qwen3-0.6B and 0.8 on Qwen2.5-1.5B. These gains replicate on fresh seeds and unseen problems, and a simple rule, that the candidate prompts are predicted to fail more often than not, predicted where they appear in five of six preregistered tests. Both gains come early in training, and standard GRPO with twice the initial learning rate comes within half a point of them. We argue that training interventions should be validated at matched compute, which overturns some apparent gains and confirms others.

Figures & tables

Appendix figures & tables38 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 7, 2026

BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation

Reinforcement learning is now central to eliciting reasoning in large language models, while in the popular algorithm Group Relative Policy Optimization (GRPO) every token in a rollout receives the same advantage. We ask how to make process supervision efficient: accelerating convergence and improving final quality without the cost of value networks. We propose Bag-of-Tokens Group Relative Policy Optimization (BoT-GRPO), which extends GRPO to token-level reward models through a length-invariant "bag of tokens" aggregation: it collects all token-level rewards across rollouts, weights each by the inverse of its source sequence length, and computes per-token advantages relative to weighted group statistics. BoT-GRPO is critic-free, and is a drop-in replacement wherever GRPO is used when token-level reward is available. On React front-end code generation, BoT-GRPO reaches 80%80\% compile rate up to 1.9×1.9\times faster than GRPO and converges faster than modern GRPO variants (GSPO, DAPO, PURE) while reaching higher final compile and VLM-judged win rates. On a second task, AIME mathematical reasoning, BoT-GRPO delivers absolute Pass@kk gains up to 8.1%8.1\% over GRPO in half the steps. For both tasks we compare the algorithm's performance on reasoning vs. non-reasoning base-model families (Qwen2.5-3B, SmolLM3-3B, Phi-4-mini-reasoning). Our experiments also yield a practical recipe for the reward model itself: reward stability matters more than richness: clean, bounded, stable fine-grained signals consistently accelerate learning where noisier alternatives stall.
Jul 29, 2026

ReCo: Reweighting GRPO Against Distributional Concentration

Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that GRPO can reduce the base model's reasoning capacity and underperform it in Pass@k when k is large, indicating reduced coverage of reasoning paths. We find that this reduction is associated with GRPO concentrating on responses that the base model already generates with high probability. We trace this concentration to two mechanisms in the GRPO update. At the response level, high-probability responses dominate the group gradient through repeated occurrence. At the token level, GRPO's importance ratio scales gradients, further reinforcing tokens that become more likely under the current policy. We propose ReCo, a reweighting method that addresses both effects. Response contributions are normalized by their expected occurrence within the rollout group, and the token-level importance ratio is replaced with a variance-based ratio that gives larger update scale to non-saturated decision points where alternative token choices remain plausible. Across Qwen2.5-Math-1.5B/7B and Llama-3.1-8B-Instruct on five mathematical reasoning benchmarks, ReCo improves Pass@k for large values of k and is comparable to GRPO for small values of k.
Nov 2, 2026

When Rewards Depend on the Group, GRPO Plays a Tournament

Rewards for diversity, coverage and distribution matching make the reward of each sampled response depend on the rest of its group, and they are now routinely optimized with GRPO and RLOO. We prove that in this setting the group-relative baseline changes the objective. The expected update equals each response's own reward gradient plus αα times its effect on its groupmates' rewards, with α=−1/(K−1)α=-1/(K-1) for groups of size KK, so GRPO trains every response to beat its groupmates in a zero-sum tournament. It cannot see a pairwise diversity bonus when K=2, sees less than half of it at any K, and often does worse than using no baseline at all. Setting α=+1α=+1 gives Team-GRPO, an unbiased estimator for any group-dependent reward that works with two samples per prompt and requires no extra model calls for pairwise rewards. The theory predicts training quantitatively. It locates the fixed points of a 9B policy to within 0.02 in ℓ1\ell_1 and predicts how concentrated trained policies become with Pearson r=0.995. On GlobalOpinionQA, GRPO collapses onto the majority answer and ends further from human opinion than the untrained model, while Team-GRPO cuts the error from 0.200.20 to 0.080.08. On NoveltyBench, Team-GRPO avoids the diversity collapse of GRPO and significantly improves set utility.