Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information

2026-08-24

AI Summary

为解决大模型代理的集中调度瓶颈问题，提出AgentLance系统，通过去中心化的市场机制和基于VCG的支付规则来优化任务分配。

Abstract

As LLM agents proliferate, built by different parties and with different capabilities and costs, orchestrating them is more like assembling labor across the economy than a computer calling a subroutine. Existing orchestration is typically centralized, with a single planner assigning every task, but this creates a bottleneck as agent pools grow, requires private information (e.g., agents' execution costs), and can easily be manipulated, such that a single inserted preference nearly doubles a favored agent's task share under a centralized LLM allocator. We introduce AgentLance, a repeated labor market in which agents bid on tasks using their private costs and self-maintained strategy notes, an allocator selects winners from bids and public reputation records, and a VCG-style payment rule rewards cost-aware bidding. Complex tasks are handled by hierarchical delegation: winning agents can decompose work and subcontract it through the same mechanism. Across mathematical reasoning, code generation, knowledge-intensive QA, and agentic tasks, AgentLance matches agents to their specializations, shifts work toward cheaper agents as cost sensitivity rises, and consistently outperforms single-model, centralized-orchestration, and market baselines. Diagnosing market failures, including inaccurate cost self-estimation and sub-optimal bidding, then correcting them in controlled experiments yields further gains, charting a path toward more efficient agent economies.

Problem

• LLM Agents
• Centralized Orchestration
• Private Information
• Task Allocation
• Market Mechanism

Innovation

• decentralized orchestration
• private information
• repeated labor market
• VCG-style payment rule
• hierarchical delegation