Allen: Rethinking MAS Design through Step-Level Policy Autonomy

• URL: http://arxiv.org/abs/2508.11294v1
• Date: Fri, 15 Aug 2025 08:02:34 GMT
• Title: Allen: Rethinking MAS Design through Step-Level Policy Autonomy
• Authors: Qiangong Zhou, Zhiting Wang, Mingyou Yao, Zongyang Liu,
• Abstract summary: We introduce a new Multi-Agent System (MAS) - Allen, designed to address two core challenges in current MAS design.<n>We have constructed a four-tier state architecture to constrain system behavior from both task-oriented and execution-oriented perspectives.<n>Allen grants unprecedented Policy Autonomy, while making a trade-off for the controllability of the collaborative structure.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a new Multi-Agent System (MAS) - Allen, designed to address two core challenges in current MAS design: (1) improve system's policy autonomy, empowering agents to dynamically adapt their behavioral strategies, and (2) achieving the trade-off between collaborative efficiency, task supervision, and human oversight in complex network topologies. Our core insight is to redefine the basic execution unit in the MAS, allowing agents to autonomously form different patterns by combining these units. We have constructed a four-tier state architecture (Task, Stage, Agent, Step) to constrain system behavior from both task-oriented and execution-oriented perspectives. This achieves a unification of topological optimization and controllable progress. Allen grants unprecedented Policy Autonomy, while making a trade-off for the controllability of the collaborative structure. The project code has been open source at: https://github.com/motern88/Allen

Related papers

• Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge [9.36518257854918]
  This paper presents a research vision for autonomous agentic systems that orchestrate collaboration within dynamic human-AI teams.<n>We propose the Autonomous Manager Agent as a core challenge: an agent that decomposes complex goals into task graphs, allocates tasks to human and AI workers, monitors progress, and maintains transparent stakeholder communication.<n>We release MA-Gym, an open-source simulation and evaluation framework for multi-agent workflow orchestration.
  arXiv  Detail & Related papers  (2025-10-02T20:51:39Z)
• JoyAgent-JDGenie: Technical Report on the GAIA [27.025464023889853]
  Large Language Models are increasingly deployed as autonomous agents for complex real-world tasks.<n>We propose a generalist agent architecture that integrates planning and execution agents with critic model voting, a hierarchical memory system spanning working, semantic, and procedural layers, and a refined tool suite for search, code execution, and multimodal parsing.
  arXiv  Detail & Related papers  (2025-10-01T04:41:58Z)
• Agentic Web: Weaving the Next Web with AI Agents [109.13815627467514]
  The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web.<n>In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users.<n>We present a structured framework for understanding and building the Agentic Web.
  arXiv  Detail & Related papers  (2025-07-28T17:58:12Z)
• Aime: Towards Fully-Autonomous Multi-Agent Framework [13.494469496862534]
  Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) are emerging as a powerful paradigm for solving complex, multifaceted problems.<n>The potential of these systems is often constrained by the prevalent plan-and-execute framework, which suffers from critical limitations.<n>This paper introduces Aime, a novel multi-agent framework designed to overcome these challenges through dynamic, reactive planning and execution.
  arXiv  Detail & Related papers  (2025-07-16T07:38:28Z)
• OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation [65.15955645757705]
  We introduce Workforce, a hierarchical multi-agent framework that decouples strategic planning from specialized execution.<n>During inference, Workforce seamlessly adapts to new domains by adding or modifying worker agents.<n>For training, we introduce optimized Workforce Learning (OWL), which improves generalization across domains.
  arXiv  Detail & Related papers  (2025-05-29T17:51:58Z)
• 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)
• Autonomous Deep Agent [0.7489814067742621]
  Deep Agent is an advanced autonomous AI system designed to manage complex multi-phase tasks.<n>The system's foundation is built on our Hierarchical Task DAG framework.<n>Deep Agent establishes a novel paradigm in self-governing AI systems.
  arXiv  Detail & Related papers  (2025-02-10T21:46:54Z)
• Position: Emergent Machina Sapiens Urge Rethinking Multi-Agent Paradigms [8.177915265718703]
  We argue that AI agents should be empowered to adjust their objectives dynamically.<n>We call for a shift toward the emergent, self-organizing, and context-aware nature of these multi-agentic AI systems.
  arXiv  Detail & Related papers  (2025-02-05T22:20:15Z)
• 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)
• Planning-oriented Autonomous Driving [60.93767791255728]
  We argue that a favorable framework should be devised and optimized in pursuit of the ultimate goal, i.e., planning of the self-driving car. We introduce Unified Autonomous Driving (UniAD), a comprehensive framework that incorporates full-stack driving tasks in one network.
  arXiv  Detail & Related papers  (2022-12-20T10:47:53Z)
• Autonomous Open-Ended Learning of Tasks with Non-Stationary Interdependencies [64.0476282000118]
  Intrinsic motivations have proven to generate a task-agnostic signal to properly allocate the training time amongst goals. While the majority of works in the field of intrinsically motivated open-ended learning focus on scenarios where goals are independent from each other, only few of them studied the autonomous acquisition of interdependent tasks. In particular, we first deepen the analysis of a previous system, showing the importance of incorporating information about the relationships between tasks at a higher level of the architecture. Then we introduce H-GRAIL, a new system that extends the previous one by adding a new learning layer to store the autonomously acquired sequences
  arXiv  Detail & Related papers  (2022-05-16T10:43:01Z)

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.