docs: Move experiment_overview &Modify mkdocs.yml

This commit is contained in:
dengjiaji 2025-09-16 21:12:54 +08:00
parent 785e78a7a1
commit d5871c11ed
3 changed files with 40 additions and 38 deletions

View file

@ -1,5 +1,8 @@
---
order: 1
---
### 🌍 [Appworld Experiment](cookbook/appworld/quickstart.md)
### 🌍 [Appworld Experiment](appworld/quickstart.md)
We tested ReMe on Appworld using qwen3-8b:
@ -12,13 +15,13 @@ Pass@K measures the probability that at least one of the K generated samples suc
score=1).
The current experiment uses an internal AppWorld environment, which may have slight differences.
You can find more details on reproducing the experiment in [quickstart.md](cookbook/appworld/quickstart.md).
You can find more details on reproducing the experiment in [quickstart.md](appworld/quickstart.md).
### 🧊 [Frozenlake Experiment](./cookbook/frozenlake/quickstart.md)
### 🧊 [Frozenlake Experiment](frozenlake/quickstart.md)
| without ReMe | with ReMe |
|:-------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------:|
| <p align="center"><img src="figure/frozenlake_failure.gif" alt="GIF 1" width="30%"></p> | <p align="center"><img src="figure/frozenlake_success.gif" alt="GIF 2" width="30%"></p> |
| without ReMe | with ReMe |
|:------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------:|
| <p align="center"><img src="../figure/frozenlake_failure.gif" alt="GIF 1" width="30%"></p> | <p align="center"><img src="../figure/frozenlake_success.gif" alt="GIF 2" width="30%"></p> |
We tested on 100 random frozenlake maps using qwen3-8b:
@ -27,9 +30,9 @@ We tested on 100 random frozenlake maps using qwen3-8b:
| without ReMe | 0.66 |
| with ReMe | 0.72 **(+6.0%)** |
You can find more details on reproducing the experiment in [quickstart.md](cookbook/frozenlake/quickstart.md).
You can find more details on reproducing the experiment in [quickstart.md](frozenlake/quickstart.md).
### 🔧 [BFCL-V3 Experiment](./cookbook/bfcl/quickstart.md)
### 🔧 [BFCL-V3 Experiment](bfcl/quickstart.md)
We tested ReMe on BFCL-V3 multi-turn-base (randomly split 50train/150val) using qwen3-8b:

View file

@ -22,18 +22,17 @@ show_datetime: true
</p>
---
ReMe provides AI agents with a unified memory system—enabling the ability to extract, reuse, and share memories across
users, tasks, and agents.
```
Personal Memory + Task Memory = Agent Memory
```
!!! info "Personal Memory + Task Memory = Agent Memory"
Personal memory helps "**understand user preferences**", while task memory helps agents "**perform better**".
---
## ✨ Architecture Design
## Architecture Design
<p align="center">
<img src="figure/reme_structure.jpg" alt="ReMe Logo" width="100%">
@ -41,31 +40,32 @@ Personal memory helps "**understand user preferences**", while task memory helps
ReMe integrates two complementary memory capabilities:
#### 🧠 **Task Memory/Experience**
!!! note "Task Memory/Experience"
Procedural knowledge reused across agents
---
- **Success Pattern Recognition**: Identify effective strategies and understand their underlying principles
- **Failure Analysis Learning**: Learn from mistakes and avoid repeating the same issues
- **Comparative Patterns**: Different sampling trajectories provide more valuable memories through comparison
- **Validation Patterns**: Confirm the effectiveness of extracted memories through validation modules
Procedural knowledge reused across agents
Learn more about how to use task memory from [task memory](task_memory/task_memory.md)
- **Success Pattern Recognition**: Identify effective strategies and understand their underlying principles
- **Failure Analysis Learning**: Learn from mistakes and avoid repeating the same issues
- **Comparative Patterns**: Different sampling trajectories provide more valuable memories through comparison
- **Validation Patterns**: Confirm the effectiveness of extracted memories through validation modules
#### 👤 **Personal Memory**
Learn more about how to use task memory from [task memory](task_memory/task_memory.md)
Contextualized memory for specific users
!!! note "Personal Memory"
- **Individual Preferences**: User habits, preferences, and interaction styles
- **Contextual Adaptation**: Intelligent memory management based on time and context
- **Progressive Learning**: Gradually build deep understanding through long-term interaction
- **Time Awareness**: Time sensitivity in both retrieval and integration
Contextualized memory for specific users
Learn more about how to use personal memory from [personal memory](personal_memory/personal_memory.md)
- **Individual Preferences**: User habits, preferences, and interaction styles
- **Contextual Adaptation**: Intelligent memory management based on time and context
- **Progressive Learning**: Gradually build deep understanding through long-term interaction
- **Time Awareness**: Time sensitivity in both retrieval and integration
---
Learn more about how to use personal memory from [personal memory](personal_memory/personal_memory.md)
## 🛠️ Installation
## Installation
### Install from PyPI (Recommended)
@ -95,7 +95,7 @@ FLOW_EMBEDDING_BASE_URL=https://xxxx/v1
---
## 🚀 Quick Start
## Quick Start
### HTTP Service Startup
@ -303,14 +303,13 @@ fetch("http://localhost:8002/retrieve_personal_memory", {
---
## 📚 Resources
-
## Resources
- **[Personal memory](personal_memory/personal_memory.md)** & **[Task memory](task_memory/task_memory.md)** : Operators used in personal memory and task memory, You can modify the config to customize the pipelines.
- **[Example Collection](cookbook/experiment_overview.md)**: Real use cases and best practices
- **[Library](./library/library.md)**: Directly use existing task memory/experience for your tasks, and you can also contribute more task memory/experience to us.
- **[Contribution](contribution.md)**: welcome to your contributions!
- **[Vector Storage Setup](vector_store_api_guide.md)**: Configure local/vector databases and usage
- **[MCP Guide](mcp_quick_start.md)**: Create MCP services
- **[personal memory](personal_memory/personal_memory.md)** & **[task memory](task_memory/task_memory.md)** : Operators used in personal memory and task memory, You can modify the config to customize the pipelines.
- **[Example Collection](./experiment_overview.md)**: Real use cases and best practices
- **[Library](./library/library.md)**: Directly use existing task memory/experience for your tasks, and you can also contribute more task memory/experience to us.
- **[Contribution](contribution.md)**: welcome to your Contributions!
---

View file

@ -34,13 +34,13 @@ nav:
- Vector Store: vector_store_api_guide.md
- Experimental Tutorials:
- Overview: experiment_overview.md
- Overview: cookbook/experiment_overview.md
- AppWorld: cookbook/appworld/quickstart.md
- BFCL: cookbook/bfcl/quickstart.md
- FrozenLake: cookbook/frozenlake/quickstart.md
- Contributions: contribution.md
- Contribution Guide: contribution.md
plugins:
- search