Hierarchical auto-organizing system for open-ended multi-agent navigation

Z Zhao, K Chen, D Guo, W Chai, T Ye, Y Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Navigating complex environments in Minecraft poses significant challenges for multi-agent
systems due to the game's dynamic and unpredictable open-world setting. Agents need to …

Do we really need a complex agent system? distill embodied agent into a single model

Z Zhao, K Ma, W Chai, X Wang, K Chen, D Guo… - arXiv preprint arXiv …, 2024 - arxiv.org
With the power of large language models (LLMs), open-ended embodied agents can flexibly
understand human instructions, generate interpretable guidance strategies, and output …

Unveiling the truth and facilitating change: Towards agent-based large-scale social movement simulation

X Mou, Z Wei, X Huang - arXiv preprint arXiv:2402.16333, 2024 - arxiv.org
Social media has emerged as a cornerstone of social movements, wielding significant
influence in driving societal change. Simulating the response of the public and forecasting …

Iterative Experience Refinement of Software-Developing Agents

C Qian, J Li, Y Dang, W Liu, YF Wang, Z Xie… - arXiv preprint arXiv …, 2024 - arxiv.org
Autonomous agents powered by large language models (LLMs) show significant potential
for achieving high autonomy in various scenarios such as software development. Recent …

Scaling Large-Language-Model-based Multi-Agent Collaboration

C Qian, Z Xie, Y Wang, W Liu, Y Dang, Z Du… - arXiv preprint arXiv …, 2024 - arxiv.org
Pioneering advancements in large language model-powered agents have underscored the
design pattern of multi-agent collaboration, demonstrating that collective intelligence can …

Large Language Model-Based Agents for Software Engineering: A Survey

J Liu, K Wang, Y Chen, X Peng, Z Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI
agents, ie, LLM-based agents. Compared to standalone LLMs, LLM-based agents …

Multi-Agent Software Development through Cross-Team Collaboration

Z Du, C Qian, W Liu, Z Xie, Y Wang, Y Dang… - arXiv preprint arXiv …, 2024 - arxiv.org
The latest breakthroughs in Large Language Models (LLMs), eg., ChatDev, have catalyzed
profound transformations, particularly through multi-agent collaboration for software …

Think-on-Process: Dynamic Process Generation for Collaborative Development of Multi-Agent System

L Lin, Y Zhou, W Chen, C Qian - arXiv preprint arXiv:2409.06568, 2024 - arxiv.org
Software development is a collaborative endeavor that requires individuals from different
departments to work together in order to collectively develop a high-quality software system …

Reframing the Relationship in Out-of-Distribution Detection

YX Lee, X Cao - arXiv preprint arXiv:2405.16766, 2024 - arxiv.org
The remarkable achievements of Large Language Models (LLMs) have captivated the
attention of both academia and industry, transcending their initial role in dialogue …

LAMBDA: A Large Model Based Data Agent

M Sun, R Han, B Jiang, H Qi, D Sun, Y Yuan… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce``LAMBDA," a novel open-source, code-free multi-agent data analysis system
that that harnesses the power of large models. LAMBDA is designed to address data …