LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu, Jizhou Guo, Yankai Chen, Chunyu Miao, Hoang Nguyen, Yue Zhou, Weizhi Zhang, Liancheng Fang, Hanrong Zhang, Fangxin Wang, Pengfei Zhang, Huacan Wang, Langzhou He, Yangning Li, Dongyuan Li, Renhe Jiang, Xue Liu, Philip S. Yu
Why It Matters
What makes this one worth your time
This survey provides valuable insights for researchers and practitioners looking to improve the reliability and safety of LLM applications in real-world scenarios.
A structured survey on enhancing LLMs through human-agent collaboration.
Summary
The paper presents a comprehensive survey of LLM-based human-agent systems (LLM-HAS), addressing the integration of human feedback and control to enhance the performance and reliability of LLMs in collaborative settings.
Key contributions
- First comprehensive survey of LLM-HAS.
- Clarification of fundamental concepts and core components of human-agent collaboration systems.
- Exploration of emerging applications and unique challenges in human-AI collaboration.
Notable insights
- The survey identifies specific components that shape LLM-HAS, such as interaction types and orchestration, which are crucial for effective collaboration.
- It highlights the importance of human feedback in mitigating the limitations of LLMs, such as hallucinations and task complexity.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2505.00753v5 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-based agents still face significant challenges, including limited reliability due to hallucinations, difficulty in handling complex tasks, and substantial safety and ethical risks, all of which limit their feasibility and trustworthiness in real-world applications. To overcome these limitations, LLM-based human-agent systems (LLM-HAS) incorporate human-provided information, feedback, or control into the agent system to enhance system performance, reliability, and safety. These human-agent collaboration systems enable humans and LLM-based agents to collaborate effectively by leveraging their complementary strengths. This paper provides the first comprehensive and structured survey of LLM-HAS. It clarifies fundamental concepts, systematically presents core components shaping these systems, including environment and profiling, human feedback, interaction types, orchestration, and communication, explores emerging applications, and discusses unique challenges and opportunities arising from human-AI collaboration. By consolidating current knowledge and offering a structured overview, we aim to foster further research and innovation in this rapidly evolving interdisciplinary field. Paper lists and resources are available at https://github.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems.