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

arXiv: https://arxiv.org/abs/2610.09804 · HTML: https://mlsanity.com/paper/2610.09804/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 39 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 12 of 12)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks](https://mlsanity.com/paper/2504.05118/) (2025)
- [StepWiser: Stepwise Generative Judges for Wiser Reasoning](https://mlsanity.com/paper/2508.19229/) (2025)
- [GRPO-λ: Credit Assignment improves LLM Reasoning](https://mlsanity.com/paper/2510.00194/) (2025)
- [GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy](https://mlsanity.com/paper/2508.04349/) (2025)
- [λ-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences](https://mlsanity.com/paper/2510.06870/) (2025)
- [Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR](https://mlsanity.com/paper/2604.11056/) (2026)
- [OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification](https://mlsanity.com/paper/2512.10756/) (2025)

## Abstract (arXiv)

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% compile rate up to 1.9× 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@k gains up to 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.