Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments

• URL: http://arxiv.org/abs/2606.03698v1
• Date: Tue, 02 Jun 2026 14:20:09 GMT
• Title: Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments
• Abstract summary: A central goal of large language model (LLM) research is to build agentic systems that can plan, act, and adapt through sustained interaction with dynamic environments.<n>We introduce Multi$2$, a hierarchical multi-agent decision-making framework that explicitly decomposes agent behavior into complementary roles.<n>A high-level agent (System 1) focuses on context-aware sub-goal generation using supervised fine-tuning (SFT), while a low-level agent (System 2) executes atomic actions through offline-to-online reinforcement learning (RL) in interactive environments.
• Score: 5.37133760455631
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A central goal of large language model (LLM) research is to build agentic systems that can plan, act, and adapt through sustained interaction with dynamic environments. While recent LLM-based agents exhibit impressive contextual reasoning, their long-horizon decision-making remains fragile, often suffering from objective drift, where goals and plans drift over extended interactions. We introduce Multi$^2$, a hierarchical multi-agent decision-making framework that explicitly decomposes agent behavior into complementary roles. A high-level agent (System 1) focuses on context-aware sub-goal generation using supervised fine-tuning (SFT), while a low-level agent (System 2) executes atomic actions through offline-to-online reinforcement learning (RL) in interactive environments. This separation enables stable long-horizon control, mitigates objective drift, and allows efficient adaptation. Across diverse interactive environments, Multi$^2$ consistently outperforms strong agentic baselines, demonstrating improved robustness and coordination in multi-turn interaction. Beyond performance, we introduce and release three hierarchical benchmark datasets, filling a long-standing gap in training and evaluating hierarchical decision-making for LLM-based agents.

Related papers

• Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks [0.0]
  Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents.<n>This paper introduces an LLM-Augmented Reinforcement Learning Agent that integrates LLM-driven planning with RL-based action optimization.
  arXiv  Detail & Related papers  (2026-08-04T11:44:07Z)
• Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution [25.26084224278813]
  Role-Agent harnesses a single Large Language Model (LLM) to function concurrently as both the agent and the environment.<n>Role-Agent consistently improves performance, yielding an average gain of over 4% over strong baselines.
  arXiv  Detail & Related papers  (2026-06-09T14:28:07Z)
• AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents [37.232397795331444]
  We present AgentCollab, a self-driven collaborative inference framework that dynamically coordinates models with different reasoning capacities during agent execution.<n>Instead of relying on external routing modules, the framework uses the agent's own self-reflection signal to determine whether the current reasoning trajectory is making meaningful progress.
  arXiv  Detail & Related papers  (2026-03-27T03:07:34Z)
• MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning [68.91090643731987]
  Deep reinforcement learning (RL) has been applied extensively to solve complex decision-making problems.<n>Existing approaches are limited to separate fields and can only handle multi-agent decision-making with a single objective.<n>We propose MO-mix to solve the multi-objective multi-agent reinforcement learning (MOMARL) problem.
  arXiv  Detail & Related papers  (2026-02-28T16:25:22Z)
• MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation [64.2621682259008]
  Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2)<n>We propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2) to integrate policy learning with multi-agent tree search.<n>We show that MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1 on challenging code generation benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T07:28:44Z)
• Multi-Agent Reinforcement Learning and Real-Time Decision-Making in Robotic Soccer for Virtual Environments [0.0]
  This paper presents a unified Multi-Agent Reinforcement Learning (MARL) framework that addresses these challenges.<n>To ensure scalability, we integrate mean-field theory into the HRL framework.<n>Our mean-field actor-critic method achieves a significant performance boost.
  arXiv  Detail & Related papers  (2025-12-02T19:11:44Z)
• MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning [3.312665722657581]
  This paper introduces the first dedicated inner-loop actor-critic framework for continuous state and action spaces.<n>We instantiate this framework with Twin Delayed Deep Deterministic Policy Gradient (TD3) and Deep Deterministic Policy Gradient (DDPG)<n>The framework combines a multi-headed actor network, a centralised critic, and an objective preference-conditioning architecture.
  arXiv  Detail & Related papers  (2025-11-22T20:24:51Z)
• Multi-Agent Tool-Integrated Policy Optimization [67.12841355267678]
  Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks.<n>Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses.<n>No existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks.
  arXiv  Detail & Related papers  (2025-10-06T10:44:04Z)
• AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning [129.44038804430542]
  We introduce AgentGym-RL, a new framework to train LLM agents for multi-turn interactive decision-making through RL.<n>We propose ScalingInter-RL, a training approach designed for exploration-exploitation balance and stable RL optimization.<n>Our agents match or surpass commercial models on 27 tasks across diverse environments.
  arXiv  Detail & Related papers  (2025-09-10T16:46:11Z)
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [77.62279834617475]
  We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
  arXiv  Detail & Related papers  (2025-06-21T18:34:43Z)
• Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization [38.68388721203677]
  We propose CollabUIAgents, a multi-agent reinforcement learning framework with a novel multi-agent credit re-assignment strategy.<n>We show that our framework improves both performance and cross-environment generalizability of multi-agent systems.
  arXiv  Detail & Related papers  (2025-02-20T12:26:15Z)
• AgentBench: Evaluating LLMs as Agents [99.12825098528212]
  Large Language Model (LLM) as agents has been widely acknowledged recently.<n>We present AgentBench, a benchmark that consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
  arXiv  Detail & Related papers  (2023-08-07T16:08:11Z)

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.