Large Language Model-based Human-Agent Collaboration for Complex Task Solving

2024/02/20 by Xueyang Feng, Feng, Xueyang, Zhiyuan Chen +11 · 11 citations
Computer Science · Engineering · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Multi-Agent Systems and Negotiation #Robotics and Automated Systems #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2402.12914

openalex publication_date 2024/02/20 · openalex created_date 2024/02/22 · openalex updated_date 2026/07/28

Abstract

In recent developments within the research community, the integration of Large Language Models (LLMs) in creating fully autonomous agents has garnered significant interest. Despite this, LLM-based agents frequently demonstrate notable shortcomings in adjusting to dynamic environments and fully grasping human needs. In this work, we introduce the problem of LLM-based human-agent collaboration for complex task-solving, exploring their synergistic potential. In addition, we propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process. We construct a human-agent collaboration dataset to train this policy model in an offline reinforcement learning environment. Our validation tests confirm the model's effectiveness. The results demonstrate that the synergistic efforts of humans and LLM-based agents significantly improve performance in complex tasks, primarily through well-planned, limited human intervention. Datasets and code are available at: https://github.com/XueyangFeng/ReHAC.

Cited by

• A Taxonomy of Confabulations and the Perception-Reality Gap in LLM-Assisted Immersive Scene Editing
• Toward Human-Centered Multi-Agent Systems: Integrating Cognition, Culture, Values, and Cooperation in AI Agents
• Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories
• Towards Unification of Hallucination Detection and Fact Verification for Large Language Models
• What's the next frontier for Data-centric AI? Data Savvy Agents
• ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation
• Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
• Understanding Post-Training Structural Changes in Large Language Models
• From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
• Mixed-Initiative Dialog for Human-Robot Collaborative Manipulation
• Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II

Related

• LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
• LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
• Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation
• Language Instructed Reinforcement Learning for Human-AI Coordination
• Efficient Human-AI Coordination via Preparatory Language-based Convention