EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems

• URL: http://arxiv.org/abs/2605.08769v1
• Date: Sat, 09 May 2026 07:55:12 GMT
• Title: EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems
• Abstract summary: EvoMAS is a framework for execution-time multi-agent workflow construction.<n>We show that EvoMAS outperforms single-agent baselines and recent automated multi-agent workflow design methods.
• Score: 10.627204426706259
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM)-based multi-agent systems have shown strong potential on complex tasks through agent specialization, tool use, and collaborative reasoning. However, most automated multi-agent system design methods still follow a one-shot paradigm: a workflow is optimized or selected before execution and then reused unchanged throughout the task. This static coordination strategy is ill-suited for long-horizon tasks whose subgoals, intermediate evidence, and information needs evolve over multiple execution stages. We propose EvoMAS, a framework for execution-time multi-agent workflow construction. EvoMAS formulates workflow construction as a meta-level sequential decision problem along a single task trajectory. At each stage, it constructs an explicit task state through a Planner-Evaluator-Updater pipeline and uses a learned Workflow Adapter to instantiate a stage-specific layered workflow from a fixed pool of candidate agents. The adapter is trained with policy gradients using sparse, verifiable terminal task success as the main supervision signal, while evaluator-based process reward is analyzed separately under very-hard sparse-reward settings. Experiments on GAIA, HLE, and DeepResearcher show that EvoMAS outperforms single-agent baselines and recent automated multi-agent workflow design methods. Our analyses further show that explicit task-state construction and learned workflow adaptation provide complementary benefits. Additional results indicate that process reward is most useful when terminal success is extremely sparse, and qualitative case studies illustrate that EvoMAS adapts agent coordination as the task state evolves.

Related papers

• From Specification to Execution: AI Assisted Scientific Workflow Management [0.7507031378170735]
  We present an AI-assisted approach to scientific workflow management.<n>The method introduces a structured specification phase that separates workflow intent, design, and implementation, allowing validation prior to code generation.<n>We evaluate the approach using a federated learning workflow for medical imaging, chosen for its parallel, iterative, and dependency-intensive structure.
  arXiv  Detail & Related papers  (2026-06-16T19:21:09Z)
• Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition [61.291733522717415]
  Agent-as-Tool is a unified parallel orchestration paradigm that mitigates both agents and tools into a standardized, learnable action space.<n>ParaManager decouples planning decisions from subtask solving, enabling state-aware parallel subtask decomposition, delegation, and asynchronous execution.<n>Experiments show that ParaManager achieves strong performance across multiple benchmarks and exhibits robust generalization under unseen model pools.
  arXiv  Detail & Related papers  (2026-04-18T14:41:27Z)
• Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System [1.4669344809969722]
  Large language models (LLMs) play a critical role in autonomous decision-making.<n>We present a scalable, hierarchical multi-agent framework for orchestrating high- throughput screening campaigns.<n>Results demonstrate that the proposed agentic framework enables efficient and scalable execution on the Aurora supercomputer.
  arXiv  Detail & Related papers  (2026-04-09T01:01:11Z)
• Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research [2.4251063179584436]
  Mimosa is an evolving multi-agent framework that automatically synthesizes task-specific multi-agents and iteratively refines them.<n>Released as a fully open-source platform, Mimosa aims to provide an open foundation for community-driven ASR.
  arXiv  Detail & Related papers  (2026-03-30T20:35:57Z)
• Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems [72.3575737073235]
  Multi-Agent Systems (MAS) solve complex tasks by coordinating multiple agents through.<n>Existing approaches generates either at task level or query level, but their relative costs and benefits remain unclear.<n>We show that query-level workflow generation is not always necessary, since a small set of top-K best task-level together already covers equivalent or even more queries.
  arXiv  Detail & Related papers  (2026-01-16T10:05:51Z)
• Towards Agentic AI for Multimodal-Guided Video Object Segmentation [14.877182670778284]
  Referring-based Video Object is a multimodal problem that requires producing fine-grained segmentation results guided by external cues.<n>Recent advances in vision-language foundation models open a promising direction toward training-free approaches.<n>We propose Multi-Modal Agent, a novel agentic system designed to solve this task in a more flexible and adaptive manner.
  arXiv  Detail & Related papers  (2025-08-14T12:11:15Z)
• 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)
• Agentic Predictor: Performance Prediction for Agentic Workflows via Multi-View Encoding [56.565200973244146]
  Agentic Predictor is a lightweight predictor for efficient agentic workflow evaluation.<n>By learning to approximate task success rates, Agentic Predictor enables fast and accurate selection of optimal agentic workflow configurations.
  arXiv  Detail & Related papers  (2025-05-26T09:46:50Z)
• 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)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• 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)

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.