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。

Ask HN: What is agent in LLM context?

1 点作者 debarshri4 个月前
I have been debating with my colleagues and it seems there is lack of clarity on what it actually means.

1 comment

lunarcave4 个月前
Anthropic has a good definition of this one [1] if you want a more comprehensive view.<p>I&#x27;ve been building something along the same lines [2]. I&#x27;d define an agent as a piece of software that can autonomously reason based on the contextual information and follow a non-pre-defined path to achieve an outcome and self-correct.<p>Most of the &quot;agents&quot; people build today have their control flow encoded in some kind of a graph. I don&#x27;t think this will yield to a useful result as reasoning capability improves. I think that setting the constraints via tool calling and letting the control flow by dynamic (with human in the loop) is the way to go.<p>[1] <a href="https:&#x2F;&#x2F;www.anthropic.com&#x2F;research&#x2F;building-effective-agents" rel="nofollow">https:&#x2F;&#x2F;www.anthropic.com&#x2F;research&#x2F;building-effective-agents</a><p>[2] <a href="https:&#x2F;&#x2F;www.inferable.ai&#x2F;blog&#x2F;posts&#x2F;functions-as-ai-agents" rel="nofollow">https:&#x2F;&#x2F;www.inferable.ai&#x2F;blog&#x2F;posts&#x2F;functions-as-ai-agents</a>