COALESCE: Economic and Security Dynamics of Skill-Based Task Outsourcing Among Team of Autonomous LLM Agents

2025-06-02

AI Summary

To address the high GPU resource overhead and deployment costs of LLM-based autonomous agent systems, this paper proposes a dynamic skill-driven autonomous outsourcing mechanism. Our method integrates explicit and implicit skill representations, enables unsupervised dynamic skill discovery, performs automatic task decomposition, and employs an ε-greedy–based multi-agent cost博弈 decision framework to achieve secure, standardized subtask outsourcing under the open Agent-to-Agent (A2A) communication standard. The core contribution is the first unified closed-loop architecture linking skill representation, task allocation, and market-level decision-making, along with a formally verifiable A2A outsourcing protocol. Theoretical analysis demonstrates a 41.8% reduction in computational cost; empirical evaluation across 240 real-world LLM tasks shows a 20.3% cost reduction, significantly enhancing system scalability and economic feasibility.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

The meteoric rise and proliferation of autonomous Large Language Model (LLM) agents promise significant capabilities across various domains. However, their deployment is increasingly constrained by substantial computational demands, specifically for Graphics Processing Unit (GPU) resources. This paper addresses the critical problem of optimizing resource utilization in LLM agent systems. We introduce COALESCE (Cost-Optimized and Secure Agent Labour Exchange via Skill-based Competence Estimation), a novel framework designed to enable autonomous LLM agents to dynamically outsource specific subtasks to specialized, cost-effective third-party LLM agents. The framework integrates mechanisms for hybrid skill representation, dynamic skill discovery, automated task decomposition, a unified cost model comparing internal execution costs against external outsourcing prices, simplified market-based decision-making algorithms, and a standardized communication protocol between LLM agents. Comprehensive validation through 239 theoretical simulations demonstrates 41.8% cost reduction potential, while large-scale empirical validation across 240 real LLM tasks confirms 20.3% cost reduction with proper epsilon-greedy exploration, establishing both theoretical viability and practical effectiveness. The emergence of proposed open standards like Google's Agent2Agent (A2A) protocol further underscores the need for frameworks like COALESCE that can leverage such standards for efficient agent interaction. By facilitating a dynamic market for agent capabilities, potentially utilizing protocols like A2A for communication, COALESCE aims to significantly reduce operational costs, enhance system scalability, and foster the emergence of specialized agent economies, making complex LLM agent functionalities more accessible and economically viable.

Problem

• Optimizing resource utilization in LLM agent systems
• Reducing operational costs via dynamic task outsourcing
• Enhancing scalability of autonomous LLM agent teams

Innovation

• Dynamic outsourcing to cost-effective third-party LLM agents
• Hybrid skill representation and dynamic skill discovery
• Market-based decision-making with standardized communication protocol