TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Survey Study on AI Agent Architectures (2024)

77 点作者 jslampe大约 1 年前

6 条评论

rck大约 1 年前
Not mentioned in the paper, but I have been experimenting with behavior trees for LLM agents, and have had a lot of success: <a href="https:&#x2F;&#x2F;richardkelley.io&#x2F;dendron&#x2F;tutorial_intro&#x2F;" rel="nofollow">https:&#x2F;&#x2F;richardkelley.io&#x2F;dendron&#x2F;tutorial_intro&#x2F;</a>
评论 #40119286 未加载
评论 #40117220 未加载
评论 #40117832 未加载
评论 #40117821 未加载
sgt101大约 1 年前
I&#x27;ll just draw folks attention to the long running AAMAS conference series.<p>Of course, it&#x27;s quite academic in nature, but it may be that some useful approaches could be picked up from this resource for LLM driven approaches.<p><a href="https:&#x2F;&#x2F;aamas2023.soton.ac.uk&#x2F;" rel="nofollow">https:&#x2F;&#x2F;aamas2023.soton.ac.uk&#x2F;</a>
评论 #40121455 未加载
irthomasthomas大约 1 年前
&quot;In the ever-evolving landscape of Natural Lan- guage Generation (NLG) evaluation, a noteworthy paradigm shift is underway as researchers increas- ingly turn their attention towards fine-tuning open- source language models (e.g., LLaMA), in lieu of traditional closed-based LLMs like ChatGPT and GPT-4. This transformative shift is propelled by a thorough exploration of key perspectives, including the expenses associated with API calls, the robust- ness of prompting, and the pivotal consideration of domain adaptability.&quot;<p>This paper was written by an LLM. Probably Claude-3.
abrichr大约 1 年前
Not mentioned: learning from demonstration. This is the approach we are taking at <a href="https:&#x2F;&#x2F;github.com&#x2F;OpenAdaptAI&#x2F;OpenAdapt">https:&#x2F;&#x2F;github.com&#x2F;OpenAdaptAI&#x2F;OpenAdapt</a>.
Havoc大约 1 年前
Finding it quite difficult to decide which platform to bet on. Autogen langchain and langgraph seem to be main contenders. And then people seem to custom roll them too
RamblingCTO大约 1 年前
perfect timing! I&#x27;m just building myself an assistant via telegram and for now went with the multi-agent collaboration via supervisor pattern.