Event ·Single source

27B参数智能体Faraday复现论文击败Claude Opus 4.8和GPT-5.5

Faraday是一个27B参数的智能体，基于Replica框架将论文复现转化为可扩展的强化学习任务。它调用编码agent作为工具，在held-out研究复现上击败了Claude Opus 4.8和GPT-5.5。奖励信号来自自动生成的rubric judge，与人类评估一致性高。论文已发布在arxiv.org/abs/2608.13331。

Current read

一个叫Faraday的27B智能体，把论文复现变成强化学习任务，在测试集上赢了Claude Opus 4.8和GPT-5.5，还把编码agent当工具用，有点意思。

2 sources79° AI heatLast updated 2026/8/14 17:00:16

Evidence

2 sources

Primary sourceelvis

2026/8/14 17:00:16View source

Related source 1Decoder

2026/8/14 16:06:32View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story