# Figure 疑似找到机器人预训练的 Scaling Law，Helix 2.5 在 30 户未见家庭中零样本成功率从 9% 升至 56%

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-09-18 04:54
- AIHOT 分数：55
- AIHOT 链接：https://aihot.news/items/cmu60zs0h039drofj0fi6uwgd
- 原文链接：https://x.com/rohanpaul_ai/status/2100689918901285245

## AI 摘要

Figure 的 Helix 2.5 端到端机器人模型在 30 户未见家庭中将零样本家庭任务成功率提升逾六倍，从 9% 升至 56%，且要求整个任务完成、无部分得分。

## 正文

Figure may have found a scaling rule for robot pretraining: keep the model and task training fixed, add more Index data (Figure's large pretraining dataset of human behavior)
and action-prediction loss falls in a clean, predictable way.

the smaller runs predicted the 8x-data run almost exactly, i.e. a robotics company can estimate what another doubling of human-behavior data will buy before spending the compute on the full run.

should make robot training less trial-and-error and more like LLM scaling, although the curve predicts action loss, not real-world task success.

so it does not yet prove equally predictable gains in robot reliability.

### 引用推文

> Rohan Paul：Figure just released this video. a beautiful robot future is indeed coming. Its Helix 2.5 model (Figure’s end-to-end robotics brain) lifted zero-shot household-...