# Tencent — When Do Larger Batches Help Scale LLM Reinforcement Learning?

- Company: Tencent (tencent.com)
- Announced: 2026-09-21T16:00:00+00:00
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://hunyuan.tencent.com/research/100116
- Record: https://forck.live/items/13339-when-do-larger-batches-help-scale-llm-reinforcement-learning
- Subject: Hunyuan

Tencent researchers investigate how batch size affects the efficiency of reinforcement learning training for large language models, analyzing the trade-off between throughput gains and sample efficiency. The study develops a framework to identify the batch size that minimizes wall-clock time to reach target performance, showing that while moderate batch increases with learning-rate retuning can improve efficiency, excessively large batches incur sample costs that outweigh throughput benefits.

## Evidence

Verbatim from https://hunyuan.tencent.com/research/100116:

> A larger batch can be either an accelerator or a speed bump. In our experiments, a moderately larger batch with learning-rate retuning preserves learning efficiency while improving throughput. But once the batch becomes too large, the additional sample cost can outweigh the throughput gain.

---

Record: https://forck.live/items/13339-when-do-larger-batches-help-scale-llm-reinforcement-learning
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md