MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems

• URL: http://arxiv.org/abs/2605.06623v1
• Date: Thu, 07 May 2026 17:35:26 GMT
• Title: MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
• Abstract summary: Large language model (LLM)-based Multi-agent systems have shown promise in tackling complex collaborative tasks.<n>We introduce MASPO, a novel framework designed to automatically and iteratively refine prompts across the entire system.<n>A core innovation of MASPO is its joint evaluation mechanism, which assesses prompts not merely by their local validity, but by their capacity to facilitate downstream success for successor agents.
• Score: 27.45439187523796
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM)-based Multi-agent systems (MAS) have shown promise in tackling complex collaborative tasks, where agents are typically orchestrated via role-specific prompts. While the quality of these prompts is pivotal, jointly optimizing them across interacting agents remains a non-trivial challenge, primarily due to the misalignment between local agent objectives and holistic system goals. To address this, we introduce MASPO, a novel framework designed to automatically and iteratively refine prompts across the entire system. A core innovation of MASPO is its joint evaluation mechanism, which assesses prompts not merely by their local validity, but by their capacity to facilitate downstream success for successor agents. This effectively bridges the gap between local interactions and global outcomes without relying on ground-truth labels. Furthermore, MASPO employs a data-driven evolutionary beam search to efficiently navigate the high-dimensional prompt space. Extensive empirical evaluations across 6 diverse tasks demonstrate that MASPO consistently outperforms state-of-the-art prompt optimization methods, achieving an average accuracy improvement of 2.9. We release our code at https://github.com/wangzx1219/MASPO.

Related papers

• MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems? [12.31270556465256]
  Multi-agent systems (MAS) offer a scalable path forward for agentic AI.<n>System prompts specify agents' roles and behaviors, enabling system-level improvements without model finetuning.<n>It remains unclear whether, when, and by how much prompt optimization improves MAS performance.
  arXiv  Detail & Related papers  (2026-06-22T17:48:40Z)
• ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks [62.031889234230725]
  6G networks rely on complex cross-layer optimization.<n> manually translating high-level intents into mathematical formulations remains a bottleneck.<n>We present ComAgent, a multi-LLM agentic AI framework.
  arXiv  Detail & Related papers  (2026-01-27T13:43:59Z)
• MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks [86.05918381895555]
  We propose MASOrchestra as a training-time framework that formulates MAS orchestration as a function-calling reinforcement learning problem.<n>In MAS-Orchestra, complex, goal-oriented subagents are abstracted as callable functions, enabling global reasoning over system structure.<n>Our analysis reveals that MAS gains depend critically on task structure, verification protocols, and the capabilities of both orchestrator and subagents.
  arXiv  Detail & Related papers  (2026-01-21T04:57:02Z)
• Achieving Equilibrium under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning [30.138706163658597]
  We propose an Agent-Attention Multi-Agent Multi-Objective Reinforcement Learning (AA-MAMORL) framework.<n>Our approach implicitly learns a joint belief over other agents' utility functions and their associated policies during training.<n>In execution, each agent independently selects actions based on local observations and its private utility function to approximate a BNE.
  arXiv  Detail & Related papers  (2025-11-12T03:06:21Z)
• MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference [40.87762929194057]
  Multi-Agent PRompt Optimization (MAPRO) is a framework that first formulates MAS prompt optimization as a Maximum a Posteriori (MAP) inference problem.<n>To address credit assignment and updates the system iteratively, MAPRO employs a topology-aware refinement mechanism.<n>Across benchmarks in various tasks, MAPRO achieves state-of-the-art performance, consistently surpassing manually engineered baselines.
  arXiv  Detail & Related papers  (2025-10-08T19:21:24Z)
• MARS: Optimizing Dual-System Deep Research via Multi-Agent Reinforcement Learning [82.14973479594367]
  Large Language Models (LLMs) for complex reasoning tasks require innovative approaches that bridge intuitive and deliberate cognitive processes.<n>This paper introduces a Multi-Agent System for Deep ReSearch (MARS) enabling seamless integration of System 1's fast, intuitive thinking with System 2's deliberate reasoning.
  arXiv  Detail & Related papers  (2025-10-06T15:42:55Z)
• Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts [75.20929587906228]
  Large Language Model (LLM)-powered multi-agent systems (MAS) have rapidly advanced collaborative reasoning, tool use, and role-specialized coordination in complex tasks.<n>However, reliability-critical deployment remains hindered by a systemic failure mode: hierarchical compliance under instruction conflicts.
  arXiv  Detail & Related papers  (2025-09-27T08:43:34Z)
• Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems [0.8437187555622164]
  Large language model (LLM) agents have shown increasing promise for collaborative task completion.<n>Existing multi-agent frameworks often rely on static, fixed roles, and limited inter-agent communication.<n>This paper proposes a coordination framework that enables adaptiveness through three core mechanisms.
  arXiv  Detail & Related papers  (2025-07-22T22:42:51Z)
• Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems [69.95482609893236]
  Large Language Model-based Multi-Agent Systems (MASs) have emerged as a powerful paradigm for tackling complex tasks through collaborative intelligence.<n>We call for a paradigm shift toward emphtopology-aware MASs that explicitly model and dynamically optimize the structure of inter-agent interactions.
  arXiv  Detail & Related papers  (2025-05-28T15:20:09Z)
• Towards more Contextual Agents: An extractor-Generator Optimization Framework [0.0]
  Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications.<n>However, their performance often degrades in context-specific scenarios, such as specialized industries or research domains.<n>To address this challenge, our work introduces a systematic approach to enhance the contextual adaptability of LLM-based agents.
  arXiv  Detail & Related papers  (2025-02-18T15:07:06Z)
• Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies [41.21314691388456]
  Large language models, employed as multiple agents that interact and collaborate with each other, have excelled at solving complex tasks.<n> Designing prompts and topologies for multi-agent systems (MAS) is inherently complex.<n>We propose Multi-Agent System Search (MASS), a MAS optimization framework that efficiently exploits the complex MAS design space.
  arXiv  Detail & Related papers  (2025-02-04T17:56:44Z)
• Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning [52.7873574425376]
  Cooperative multi-agent reinforcement learning (MARL) faces significant scalability issues due to state and action spaces that are exponentially large in the number of agents. We propose a novel, value-based multi-agent algorithm called LOMAQ, which incorporates local rewards in the Training Decentralized Execution paradigm.
  arXiv  Detail & Related papers  (2021-09-22T10:08:15Z)

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.