yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-09-27 17:20:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

update (#2178)

Browse Source 
Co-authored-by: AnonymousRepoSub <“shaokunzhang529@outlook.com” >
This commit is contained in:
Shaokun Zhang 2024-03-28 01:11:20 -04:00 committed by GitHub
parent e6237d44a1
commit dd61eaae43
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
website/blog/2023-12-23-AgentOptimizer/index.mdx
View File

@ -12,10 +12,12 @@ tags: [LLM, research]
**TL;DR:** **TL;DR:**
Introducing **AgentOptimizer**, a new class for training LLM agents in the era of LLMs as a service. Introducing **AgentOptimizer**, a new class for training LLM agents in the era of LLMs as a service.
**AgentOptimizer** is able to prompt LLMs to iteratively optimize function/skills of AutoGen agents according to the historical conversation and performance. **AgentOptimizer** is able to prompt LLMs to iteratively optimize function/skills of AutoGen agents according to the historical conversation and performance.
Checkout one implementation for **AgentOptimizer** on [MATH](https://github.com/hendrycks/math) dataset
[here](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_agentoptimizer.ipynb).
More information could be found in the [paper](https://arxiv.org/abs/2402.11359). More information could be found in:
**Paper**: https://arxiv.org/abs/2402.11359.
**Notebook**: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_agentoptimizer.ipynb.
## Introduction ## Introduction
In the traditional ML pipeline, we train a model by updating its weights according to the loss on the training set, while in the era of LLM agents, how should we train an agent? In the traditional ML pipeline, we train a model by updating its weights according to the loss on the training set, while in the era of LLM agents, how should we train an agent?