Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
| Date | Stars |
|---|---|
| 2026-07-31 | 449 |
| 2026-08-03 | 449 |
| 2026-08-13 | 451 |
| 2026-08-18 | 449 |
| 2026-08-21 | 449 |
| 2026-08-25 | 450 |
| 2026-09-10 | 451 |
| 2026-09-20 | 451 |
Today
— stars today
This week
— stars this week
This month
+2 stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h2>Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving</h2>
</div>
<div align="center">
<a href='https://arxiv.org/abs/2507.06229'><img src='https://img.shields.io/badge/AGENT KB-arXiv-d63031?logo=arxiv&logoColor=white'></a>
<a href='https://www.python.org/downloads/release/python-31210/'><img src='https://img.shields.io/badge/Python-3.12-green'></a>
<a href='https://github.com/OPPO-PersonalAI/OAgents/blob/main/LICENSE'><img src='https://img.shields.io/badge/License-Apache%202.0-blue'></a>
</div>
This is the official repository for the paper "Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving" **(ICML 2025 CFAgentic Workshop Best Paper Runner-Up Award)**.
The work is done by [Xiangru Tang*](https://xiangrutang.github.io/), Tianrui Qin*, Tianhao Peng*, Ziyang Zhou, Daniel Shao, Tingting Du, Xinming Wei, Peng Xia, Fang Wu, He Zhu, Ge Zhang, Jiaheng Liu, Xingyao Wang, Sirui Hong, Chenglin Wu, Hao Cheng, Chi Wang, [Wangchunshu Zhou](https://michaelzhouwang.github.io/).
<div align="center">
<img src="./assets/agent_kb.png" width="80%" height="auto" />
</div>
## Key Features of Agent KB
- Hierarchical Memory Structure: Combines working memory, episodic memory, and semantic knowledge base.
- Agentic Reasoning: Supports autonomous decision-making and planning using LLMs.
- Cross-Domain Adaptability: Designed for generalization across different task domains (e.g., QA, coding, planning).
- Modular Design: Easy to integrate with various benchmarks and environments.
## GAIA Part
To start, follow the steps below:
### Access to the main part of GAIA
```bash
cd ./Agent-KB-GAIA/examples/open_deep_research
```
---
### Install dependencies
Run the following command to install the required dependencies from the `requirements.txt` file:
```bash
pip install -r requirements.txt
```
---
### Install the development version of `smolagents`
```bash
pip install -e ../../.[dev]
```
#### Set up environment variables
The agent uses the `SearchTool` for web search, which requires an environment variable with the corresponding API key, based on the selected provider:
- `SERP_API_KEY` for SerpApi: [Sign up here to get a key](https://serpapi.com/users/sign_up)
Depending on the model you want to use, you may need to set environment variables. You need to set the `OPENAI_BASE_URL` and `OPENAI_API_KEY` environment variable.
---
### Usage test
#### Step 1: Prepare the Data
Download the GAIA dataset and place it under the following directory:
```
./data/gaia
```
The expected directory structure is as follows:
```
├── data
│ ├── gaia
│ ├── test
│ └── validation
```
#### Step 2: Test run on GAIA
You're now all set to run on GAIA! Simply execute the run_gaia.py script like so:
```bash
python run_gaia.py --model-id openai:gpt-4.1 --model-id-search openai:gpt-4.1 --run-name gpt-4.1-gaia
```
If you'd like to use different questions or datasets, you can refer to the run_gaia.py script for guidance and make the necessary adjustments.
---
### Agent KB usage
Now, let's start configuring Agent KB.
#### Step 1: Prepare the Knowledge Base Data
Format your knowledge base samples properly and save them in the following file:
```
./agent_kb/agent_kb_database.json
```
Each sample in the JSON file should follow this structure:
```
{
"question": "",
"agent_planning": "",
"search_agent_planning": "",
"agent_experience": "",
"search_agent_experience": ""
}
```
#### Step 2: Start the Agent KB Service
Launch the Agent KB service by running the script below:
```bash
python ./agent_kb/agent_kb_service.py
```
#### Step 3: Execute the Run Command
Once everything is configured, run the main script using a command similar to the following example:
```bash
python run_gaia.py --model-id openai:gpt-4.1 --model-id-search openai:gpt-4.1 --run-name gpt-4.1-gaia --agent_kb --concurrency 1
```
---
## SWE-bench Part
### Access to main part of SWE-bench
```bash
cd ./AExcerpt of 8,143 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:02c877a64ecc3ac4, llm:Repository title and description: 'Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving' — suggests knowledge base for agents, enabling agentic problem solving and cross-domain experience reuse.
matched fp:02c877a64ecc3ac4, llm:Repository title and description: 'Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving' — suggests knowledge base for agents, enabling agentic problem solving and cross-domain experience reuse.
matched fp:02c877a64ecc3ac4, llm:Repository title and description: 'Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving' — suggests knowledge base for agents, enabling agentic problem solving and cross-domain experience reuse.