发表机构
University of Chicago; University of Virginia; Tsinghua University; Zhongguancun Academy; Santa Fe Institute（芝加哥大学; 弗吉尼亚大学; 清华大学; 中关村学院; 圣塔菲研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对中心化LLM智能体协调的瓶颈与易操控问题，提出去中心化的AgentLance重复劳动力市场机制，经多类任务验证，其匹配专长、转向廉价智能体的表现优于基线方法，还可通过修正市场失灵进一步提升效率。
AI 中文摘要
随着由不同主体构建、具备不同能力与成本的大语言模型（LLM）智能体不断增多，对它们的协调更类似于整合经济中的各类劳动力，而非计算机调用子程序。现有协调方式通常是中心化的，由单一规划者分配所有任务，但随着智能体池扩大，这种方式会形成瓶颈，还会需要私有信息（如智能体的执行成本），且极易被操控——例如在中心化LLM分配器下，仅需插入一个偏好，就能使受青睐智能体的任务份额几乎翻倍。我们提出AgentLance，这是一种重复性劳动力市场：智能体利用自身私有成本与自行维护的策略笔记对任务竞标，分配器从竞标结果与公开声誉记录中选择中标者，且采用VCG式支付规则奖励考虑成本的竞标；复杂任务通过层级委托处理，中标智能体可分解工作并通过相同机制分包。在数学推理、代码生成、知识密集型问答及智能体任务中，AgentLance能将智能体与其专长匹配，随成本敏感度提升将工作转向更廉价的智能体，且始终优于单模型、中心化协调及市场基线方法；通过诊断市场失灵（包括不准确的成本自我估计与非最优竞标）并在受控实验中修正，可进一步提升性能，为构建更高效的智能体经济指明了方向。
英文摘要
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.
CommentsWorking paper
