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

• URL: http://arxiv.org/abs/2608.23867v1
• Date: Mon, 24 Aug 2026 22:15:37 GMT
• Title: Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information
• Abstract summary: We introduce AgentLance, a labor market in which agents bid on tasks using their private costs and self-maintained strategy notes.<n>AgentLance consistently outperforms single-model, centralized-orchestration, and market baselines.
• Score: 16.55988307561715
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• EASy: Towards Efficient LLM-Based Agentic System [54.10819421625103]
  We propose EASy, a trainable agentic framework that jointly optimize task performance and computational efficiency through reinforcement learning.<n> EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing.<n>It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes.
  arXiv  Detail & Related papers  (2026-08-05T08:50:36Z)
• Benchmarking Open-Ended Multi-Agent Coordination in Language Agents [48.1363632826625]
  Alem embeds procedurally generated coordination tasks, soft specialisation, communication, and controllable coordination difficulty into a long-horizon survival world.<n>We introduce $alem$, a JAX-based benchmark for open-ended multi-agent coordination built on Craftax-like dynamics.
  arXiv  Detail & Related papers  (2026-06-06T21:13:43Z)
• Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions [80.74432115171285]
  We study how a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control.<n>Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards.<n>We show that, with weak agents, the economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks.
  arXiv  Detail & Related papers  (2026-06-01T20:21:09Z)
• A Novel Hierarchical Multi-Agent System for Payments Using LLMs [1.8717456484053328]
  This research proposes the Hierarchical Multi-Agent System for Payments (HMASP), which provides an end-to-end agentic method for completing payment.<n>To our knowledge, HMASP is the first LLM-based multi-agent system to implement end-to-end agentic payment.
  arXiv  Detail & Related papers  (2026-02-27T14:58:13Z)
• Scaling Small Agents Through Strategy Auctions [6.863341991827782]
  We show that small agents' performance fails to scale with task complexity on deep search and coding tasks.<n>We introduce Strategy Auctions for Workload Efficiency, an agent framework inspired by freelancer marketplaces.<n>We show that SALE reduces reliance on the largest agent by 53%, lowers overall cost by 35%, and consistently improves upon the largest agent's pass@1.
  arXiv  Detail & Related papers  (2026-02-02T20:05:51Z)
• COALESCE: Economic and Security Dynamics of Skill-Based Task Outsourcing Among Team of Autonomous LLM Agents [0.0]
  COALESCE is a novel framework designed to enable autonomous Large Language Model (LLM) agents to outsource specific subtasks to specialized, cost-effective third-party LLM agents.<n> Comprehensive validation through 239 theoretical simulations demonstrates 41.8% cost reduction potential.<n>Large-scale empirical validation across 240 real LLM tasks confirms 20.3% cost reduction with proper epsilon-greedy exploration.
  arXiv  Detail & Related papers  (2025-06-02T17:22:47Z)
• The Real Barrier to LLM Agent Usability is Agentic ROI [110.31127571114635]
  Large Language Model (LLM) agents represent a promising shift in human-AI interaction.<n>We highlight a critical usability gap in high-demand, mass-market applications.
  arXiv  Detail & Related papers  (2025-05-23T11:40:58Z)
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration [55.35849138235116]
  We propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($textDyLAN$) for LLM-powered agent collaboration. We demonstrate that DyLAN outperforms strong baselines in code generation, decision-making, general reasoning, and arithmetic reasoning tasks with moderate computational cost.
  arXiv  Detail & Related papers  (2023-10-03T16:05:48Z)
• Many learning agents interacting with an agent-based market model [0.0]
  We consider the dynamics of learning optimal execution trading agents interacting with a reactive Agent-Based Model. The model represents a market ecology with 3-trophic levels represented by: optimal execution learning agents, minimally intelligent liquidity takers, and fast electronic liquidity providers. We examine whether the inclusion of optimal execution agents that can learn is able to produce dynamics with the same complexity as empirical data.
  arXiv  Detail & Related papers  (2023-03-13T18:15:52Z)
• Multi-Agent Neural Rewriter for Vehicle Routing with Limited Disclosure of Costs [65.23158435596518]
  Solving the multi-vehicle routing problem as a team Markov game with partially observable costs. Our multi-agent reinforcement learning approach, the so-called multi-agent Neural Rewriter, builds on the single-agent Neural Rewriter to solve the problem by iteratively rewriting solutions.
  arXiv  Detail & Related papers  (2022-06-13T09:17:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.