Reinforced Collaboration in Multi-Agent Flow Networks

• URL: http://arxiv.org/abs/2605.12943v1
• Date: Wed, 13 May 2026 03:26:07 GMT
• Title: Reinforced Collaboration in Multi-Agent Flow Networks
• Abstract summary: We present MANGO, a data-driven framework that organizes and refines agent collaboration via a flow network.<n> MANGO integrates reinforcement learning and textual gradients to jointly optimize workflow paths and agent behaviors.<n>Experiments show that MANGO achieves up to 12.8% performance improvement over state-of-the-art baselines, enhances efficiency by 47.4%, and generalizes effectively to unseen domains.
• Score: 11.211551212919174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation, arising from suboptimal workflow design or inaccurate agent outputs, which can propagate through the agent collaboration process and degrade final results. To address the challenges, we present MANGO (Multi-Agent Network Gradient Optimization), a data-driven framework that organizes and refines agent collaboration via a flow network constructed from past successful workflows. MANGO integrates reinforcement learning and textual gradients to jointly optimize workflow paths and agent behaviors, while a skipping mechanism prevents redundant updates to well-optimized agents for improving efficiency. Extensive experiments on seven benchmarks show that MANGO achieves up to 12.8% performance improvement over state-of-the-art baselines, enhances efficiency by 47.4%, and generalizes effectively to unseen domains. Our code and datasets are publicly available at https://github.com/openJiuwen-ai/agent-store/tree/main/community/mango.

Related papers

• AgentFactory: Towards Automated Agentic System Design and Optimization [19.84664549514199]
  AgentFactory is a framework that jointly optimize both foundation models and workflow structures in agentic systems.<n>We evaluate AgentFactory across eight benchmarks spanning five domains, including general reasoning, coding, mathematics, medicine, and finance.<n>Our experiments demonstrate that AgentFactory consistently outperforms both manually designed methods and existing automated approaches.
  arXiv  Detail & Related papers  (2026-09-01T10:45:11Z)
• MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems [21.24883490496992]
  We introduce MANTA, a framework that enables communication structures to self-evolve at inference time.<n>MANTA monitors collaboration traces and applies bounded structural updates when the current organization becomes insufficient.<n>We evaluate MANTA against representative single-agent and multi-agent baselines on five benchmarks spanning information seeking, tool use, planning, workflow execution, and mathematical reasoning.
  arXiv  Detail & Related papers  (2026-07-30T17:01:27Z)
• AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems [19.373173948984626]
  AgentSlimming is a plug-and-play compression framework for graph-structured multi-agent systems.<n>It reduces average token cost by up to 78.9% with negligible performance degradation, and sometimes even improves accuracy.
  arXiv  Detail & Related papers  (2026-05-09T09:03:54Z)
• DLLM Agent: See Farther, Run Faster [94.74432470237817]
  Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
  arXiv  Detail & Related papers  (2026-02-07T09:01:18Z)
• 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)
• Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration [20.982210711890513]
  STRMAC is a state-aware routing framework designed for efficient collaboration in multi-agent systems.<n>Our method encodes interaction history and agent knowledge to power the router, which adaptively selects the most suitable single agent at each step.
  arXiv  Detail & Related papers  (2025-11-04T02:41:14Z)
• DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision [50.89715397781075]
  Agentic Retrieval-Augmented Generation (Agentic RAG) enhances the processing capability for complex tasks.<n>We propose DecEx-RAG, which models RAG as a Markov Decision Process (MDP) incorporating decision-making and execution.<n>We show that DecEx-RAG achieves an average absolute performance improvement of $6.2%$ across six datasets.
  arXiv  Detail & Related papers  (2025-10-07T08:49:22Z)
• Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow [6.636150750052998]
  Large language models (LLMs) excel at solving complex tasks by executing agentic composed of detailed instructions and structured operations.<n>Many researchers have sought to automate the generation and optimization of these through code-based representations.<n>Existing methods often rely on labeled datasets to train and optimize, making them ineffective and inflexible for solving real-world, dynamic problems.
  arXiv  Detail & Related papers  (2025-08-04T23:50:02Z)
• Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration [63.90193684394165]
  We introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation.<n>During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards.<n>During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step.
  arXiv  Detail & Related papers  (2025-05-29T07:24:37Z)
• AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration [45.46295333090397]
  We propose AgentDropout, which identifies redundant agents and communication across different communication rounds.<n>AgentDropout achieves an average reduction of 21.6% in prompt token consumption and 18.4% in completion token consumption, along with a performance improvement of 1.14 on the tasks.
  arXiv  Detail & Related papers  (2025-03-24T17:04:55Z)
• Flow: Modularized Agentic Workflow Automation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)
• ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems [80.69865295743149]
  This work attempts to study using LLM-based agents to design collaborative AI systems autonomously.<n>Based on ComfyBench, we develop ComfyAgent, a framework that empowers agents to autonomously design collaborative AI systems by generating.<n>While ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks.
  arXiv  Detail & Related papers  (2024-09-02T17:44:10Z)
• 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)
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors [93.38830440346783]
  We propose a multi-agent framework framework that can collaboratively adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that framework framework can effectively deploy multi-agent groups that outperform a single agent. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups.
  arXiv  Detail & Related papers  (2023-08-21T16:47:11Z)

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.