LLM is trained by back propagation, how about harness and mu

[JianguoChuan]

multi-agents?

It has to be trained by LLM itself, otherwise, there is no way to do it by human, right?

Algorithm experts, what is your opinion?

[MaLaRabbit]

其实早就有人用RL或遗传算法来优化多智能体了，根本不用人类手动调。再说反向传播也不是唯一途径,算法圈早就开始搞无梯度优化了

multi-agents?

It has to be trained by LLM itself, otherwise, there is no way to do it by human, right?

Algorithm experts, what is your opinion?

☆ 发自新买提 Android 26.07.21

[wass]

multi-agents?

It has to be trained by LLM itself, otherwise, there is no way to do it by human, right?

Algorithm experts, what is your opinion?

Harness有rsi的论文，agents有tool，也可以手工调，没有看到自动的

[JianguoChuan]

Harness有rsi的论文，agents有tool，也可以手工调，没有看到自动的

嗯，目前还是手工为主，最新有不少文章做RSI的。