HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents

• URL: http://arxiv.org/abs/2603.00977v1
• Date: Sun, 01 Mar 2026 08:09:03 GMT
• Title: HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents
• Authors: Hongbo Jin, Rongpeng Zhu, Jiayu Ding, Wenhao Zhang, Ge Li,
• Abstract summary: HiMAC is a hierarchical agentic RL framework that decomposes long-horizon decision-making into macro-level planning and micro-level execution.<n>Our results show that introducing structured hierarchy, rather than increasing model scale alone, is a key factor for enabling robust long-horizon agentic intelligence.
• Score: 19.63866851076813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing approaches predominantly rely on flat autoregressive policies, where high-level reasoning and low-level actions are generated within a single token sequence, leading to inefficient exploration and severe error propagation over extended trajectories. In this work, we propose HiMAC, a hierarchical agentic RL framework that explicitly decomposes long-horizon decision-making into macro-level planning and micro-level execution. HiMAC models reasoning as a structured blueprint generation process followed by goal-conditioned action execution, enabling robust long-horizon planning within LLM-based agents. To train this hierarchy efficiently, we introduce a critic-free hierarchical policy optimization paradigm that extends group-based reinforcement learning to bi-level structures through hierarchical relative advantage estimation. Furthermore, we propose an iterative co-evolution training strategy that alternates between planner exploration and executor adaptation, mitigating the non-stationarity inherent in hierarchical learning. Extensive experiments on ALFWorld, WebShop, and Sokoban demonstrate that HiMAC consistently outperforms strong prompting and reinforcement learning baselines, achieving state-of-the-art performance and substantially improved sample efficiency across both text-based and visually grounded environments. Our results show that introducing structured hierarchy, rather than increasing model scale alone, is a key factor for enabling robust long-horizon agentic intelligence.

Related papers

• HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents [36.77027704958893]
  HiPER is a novel Hierarchical Plan-Execute RL framework that separates high-level planning from low-level execution.<n>HiPER achieves state-of-the-art performance on challenging interactive benchmarks, reaching 97.4% success on ALFWorld and 83.3% on WebShop with Qwen2.5-7B-Instruct.
  arXiv  Detail & Related papers  (2026-02-18T03:31:34Z)
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts [63.412646471177645]
  We propose a novel Reinforced Strategy Optimization (RSO) method for Conversational Recommender Systems (CRSs)<n>RSO decomposes the process of generating strategy-driven response decisions into the macro-level strategy planning and micro-level strategy adaptation.<n>Experiments show that RSO significantly improves interaction performance compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-09-30T11:12:01Z)
• Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning [56.496001894673235]
  Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs)<n>Our analysis reveals that puzzling phenomena like aha moments", length-scaling'' and entropy dynamics are not disparate occurrences but hallmarks of an emergent reasoning hierarchy.
  arXiv  Detail & Related papers  (2025-09-03T18:52:49Z)
• HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents [29.437416274639165]
  HERAKLES is a framework that enables a two-level hierarchical autotelic agent to continuously compile mastered goals into a low-level policy.<n>We show that it scales effectively with goal complexity, improves sample efficiency through skill compilation, and enables the agent to adapt robustly to novel challenges over time.
  arXiv  Detail & Related papers  (2025-08-20T14:50:28Z)
• Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning [5.274804664403783]
  Strict Subgoal Execution (SSE) is a graph-based hierarchical RL framework that enforces single-step subgoal reachability.<n>We show that SSE consistently outperforms existing goal-conditioned RL and hierarchical RL approaches in both efficiency and success rate.
  arXiv  Detail & Related papers  (2025-06-26T06:35:42Z)
• Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning [32.260964481673085]
  Large language models (LLMs) struggle with long-horizon decision-making tasks due to deficient exploration and long-term credit assignment.<n>We propose an innovative framework that introduces a parameter-efficient and generally applicable hierarchy to LLM policies.<n>We develop a scheme where the low-level controller is supervised with abstract, step-by-step plans that are learned and instructed by the high-level policy.
  arXiv  Detail & Related papers  (2025-05-26T09:43:40Z)
• Structured Agent Distillation for Large Language Model [56.38279355868093]
  We propose Structured Agent Distillation, a framework that compresses large LLM-based agents into smaller student models.<n>Our method segments trajectories into [REASON] and [ACT] spans, applying segment-specific losses to align each component with the teacher's behavior.<n>Experiments on ALFWorld, HotPotQA-ReAct, and WebShop show that our approach consistently outperforms token-level and imitation learning baselines.
  arXiv  Detail & Related papers  (2025-05-20T02:01:55Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Feudal Graph Reinforcement Learning [18.069747511100132]
  Graph-based representations and message-passing modular policies constitute prominent approaches to tackling composable control problems in reinforcement learning (RL)<n>We propose a novel methodology, named Feudal Graph Reinforcement Learning (FGRL), that addresses such challenges by relying on hierarchical RL and a pyramidal message-passing architecture.<n>In particular, FGRL defines a hierarchy of policies where high-level commands are propagated from the top of the hierarchy down through a layered graph structure.
  arXiv  Detail & Related papers  (2023-04-11T09:51:13Z)
• Provable Hierarchy-Based Meta-Reinforcement Learning [50.17896588738377]
  We analyze HRL in the meta-RL setting, where learner learns latent hierarchical structure during meta-training for use in a downstream task. We provide "diversity conditions" which, together with a tractable optimism-based algorithm, guarantee sample-efficient recovery of this natural hierarchy. Our bounds incorporate common notions in HRL literature such as temporal and state/action abstractions, suggesting that our setting and analysis capture important features of HRL in practice.
  arXiv  Detail & Related papers  (2021-10-18T17:56:02Z)

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.