Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: ReasoningAgent blog links #268

Merged
merged 1 commit into from
Dec 22, 2024
Merged

fix: ReasoningAgent blog links #268

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion website/blog/2024-12-02-ReasoningAgent2/index.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,13 +70,15 @@ tags: [LLM, GPT, research]
</CardGroup>
</div>

![Tree of Thoughts](img/reasoningagent_1.png)
<iframe width="560" height="315" src="https://www.youtube.com/embed/sS8Q5yMuEhs?si=MfWmzflK94S94FEx" title="ReasoningAgent" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

**TL;DR:**
* We introduce **ReasoningAgent**, an AG2 agent that implements tree-of-thought reasoning with beam search to solve complex problems.
* ReasoningAgent explores multiple reasoning paths in parallel and uses a grader agent to evaluate and select the most promising paths.
* The exploration trajectory and thought tree can be saved locally for further analysis. These logs can even be saved as SFT dataset and preference dataset for DPO and PPO training.

![Tree of Thoughts](img/reasoningagent_1.png)

## Introduction

Large language models (LLMs) have shown impressive capabilities in various tasks, but they can still struggle with complex reasoning problems that require exploring multiple solution paths. To address this limitation, we introduce ReasoningAgent, an AG2 agent that implements tree-of-thought reasoning with beam search.
Expand Down
4 changes: 3 additions & 1 deletion website/blog/2024-12-20-Reasoning-Update/index.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ tags: [LLM, GPT, research, tutorial]
</CardGroup>
</div>

![Tree of Thoughts](img/mcts_example.png)
<iframe width="560" height="315" src="https://www.youtube.com/embed/W7hfRA7XXjI?si=ImwXfHIYGosmaRFi" title="Reasoning Agent with MCTS" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

**Key Updates in this Release:**

Expand All @@ -74,6 +74,8 @@ tags: [LLM, GPT, research, tutorial]
* New `forest_size` parameter enables maintaining multiple independent reasoning trees
* Support for ground truth answers in prompts to generate training data for LLM fine-tuning

![Tree of Thoughts](img/mcts_example.png)

## Introduction

In our [previous post](https://docs.ag2.ai/blog/2024-12-02-ReasoningAgent2/), we introduced the ReasoningAgent, which utilized Beam Search for systematic reasoning. Today, we include MCTS (Monte Carlo Tree Search) and Language Agent Tree Search (LATS) as alternative search strategies, which present advantages in different scenarios.
Expand Down
Loading