✨✨✨Cheer 08/2026

Our paper is PUBLICATED in Sustainable Cities and Society (IF=13.3) https://www.sciencedirect.com/science/article/abs/pii/S2210670726007304

🚀🚀 Update 07/29/2026

The data and resources are updated as highlighted🟨 below.

🚀🚀 Update 07/29/2026

Some figures are available for public now:

Fig. S5 Agents' performance on coordinating multiple contested interests for LNR

Fig. S4 Examples of typical task failure

Fig. S3 Comparison of outputs generated by T-ARR-01 and corresponding study

Fig. S2 Comparison of outputs generated by T-SRS-09 and corresponding study

Fig. S1 Comparison of outputs generated by T-ICF-06 and corresponding study

📣 Important Notice

⚠️ As the paper is under review, all contents in this repository are currently not permitted for reuse by anyone until this announcement is removed. Thank you for your understanding! 🙏

1. Overview & Objectives

This repository contains the complete implementation, experimental data, and supplementary results for the paper ××× developed by XXX University in China, and .

Pending publication, the code is shared under a restrictive license. Once the paper is accepted, the repository will transition to a MIT license. Please contact the corresponding author for any inquiries regarding academic use during the review period.

2. Videos of agents operation

2.1 Operation of the developed prototype

↓↓↓ A demonstration of using the developed prototype to operate the TCG-TE LNR agents using graph-guided MCP tools

The full video could be found here

↓↓↓ A demonstration of using the developed prototype to integrate a new MCP server to TCG-TE LNR agents

The full video could be found here

2.2 Operation of agents based on NPG-TE pattern

2.2.1 Operation of agents based on NPG-TE pattern enabled by ReAct

↓↓↓ A snippet of the operation of NPG-TE (ReAct) agent with discrete MCP tools driven by GPT-5.

↓↓↓ A screenshot of Agent's response

The full video can be found here

↓↓↓ A snippet of the operation of NPG-TE (ReAct) agents with discrete MCP tools driven by GPT-4o.

↓↓↓ A screenshot of Agent's response

The full video can be found here

2.2.2 Operation of agents based on NPG-TE pattern enabled by GoT

↓↓↓ A snippet of the operation of NPG-TE (GoT) agent with discrete MCP tools driven by GPT-5.

The full video can be found here

↓↓↓ A snippet of the operation of NPG-TE (GoT) agent with discrete MCP tools driven by Deepseek-V3.

The full video can be found here

2.2.3 Operation of agents based on NPG-TE pattern enabled by PE

↓↓↓ A snippet of the operation of NPG-TE (PE) agent with discrete MCP tools driven by GPT-4o.

The full video can be found here

2.3 Operation of agents based on TCG-TE pattern

↓↓↓ A snippet of the operation of TCG-TE agents with graph-guided MCP tools driven by Claude sonnet 3.7.

The full video can be found here

↓↓↓ A snippet of the operation of TCG-TE agents with graph-guided MCP tools driven by GPT-4.1.

↓↓↓ A screenshot of Agent's response

The full video can be found here

3. Repository Structure

4. Acknowledgments

This work heavily relies on excellent open-source projects, including but not limited to:

• LangGraph & LangChain

• Hugging Face MTEB leaderboard

• NetworkX, PyTorch Geometric, and numerous LLM providers (OpenAI, Anthropic, Qwen, Llama, etc.)

We are deeply grateful to all contributors of these foundational work.