HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents

• URL: http://arxiv.org/abs/2602.16165v1
• Date: Wed, 18 Feb 2026 03:31:34 GMT
• Title: HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents
• Authors: Jiangweizhi Peng, Yuanxin Liu, Ruida Zhou, Charles Fleming, Zhaoran Wang, Alfredo Garcia, Mingyi Hong,
• Abstract summary: 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.
• Score: 36.77027704958893
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful feedback. Most existing reinforcement learning (RL) approaches model LLM agents as flat policies operating at a single time scale, selecting one action at each turn. In sparse-reward settings, such flat policies must propagate credit across the entire trajectory without explicit temporal abstraction, which often leads to unstable optimization and inefficient credit assignment. We propose HiPER, a novel Hierarchical Plan-Execute RL framework that explicitly separates high-level planning from low-level execution. HiPER factorizes the policy into a high-level planner that proposes subgoals and a low-level executor that carries them out over multiple action steps. To align optimization with this structure, we introduce a key technique called hierarchical advantage estimation (HAE), which carefully assigns credit at both the planning and execution levels. By aggregating returns over the execution of each subgoal and coordinating updates across the two levels, HAE provides an unbiased gradient estimator and provably reduces variance compared to flat generalized advantage estimation. Empirically, 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 (+6.6\% and +8.3\% over the best prior method), with especially large gains on long-horizon tasks requiring multiple dependent subtasks. These results highlight the importance of explicit hierarchical decomposition for scalable RL training of multi-turn LLM agents.

Related papers

• HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents [19.63866851076813]
  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.
  arXiv  Detail & Related papers  (2026-03-01T08:09:03Z)
• Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning [0.9453554184019106]
  Multi-robot task planning requires decomposing natural-language instructions into executable actions.<n>PDDL planners provide rigorous guarantees but struggle to handle ambiguous or long-horizon missions.<n>We present a hierarchical multi-agent LLM-based planner with prompt optimization.
  arXiv  Detail & Related papers  (2026-02-25T08:08:26Z)
• ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning [6.600538353483611]
  We propose a hierarchical task-planning method that decomposes a complex goal into more manageable subgoals within a dynamically constructed agent tree.<n>ReAcTree consistently outperforms strong task-planning baselines such as ReAct across diverse large language models.
  arXiv  Detail & Related papers  (2025-11-04T09:55:40Z)
• ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents [61.51091799997476]
  We introduce ReCAP (Recursive Context-Aware Reasoning and Planning), a hierarchical framework with shared context for reasoning and planning in large language models (LLMs)<n>ReCAP combines three key mechanisms: plan-ahead decomposition, structured re-injection of parent plans, and memory-efficient execution.<n>Experiments demonstrate that ReCAP substantially improves subgoal alignment and success rates on various long-horizon reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T20:03:55Z)
• Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents [56.625878022978945]
  Large Language Models (LLMs) as autonomous agents are increasingly tasked with solving complex, long-horizon problems.<n>Direct Preference Optimization (DPO) provides a signal that is too coarse for precise credit assignment, while step-level DPO is often too myopic to capture the value of multi-step behaviors.<n>We introduce Hierarchical Preference Learning (HPL), a hierarchical framework that optimize LLM agents by leveraging preference signals at multiple, synergistic granularities.
  arXiv  Detail & Related papers  (2025-09-26T08:43:39Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• 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)
• Proposing Hierarchical Goal-Conditioned Policy Planning in Multi-Goal Reinforcement Learning [0.0]
  We propose a method combining reinforcement learning and automated planning.<n>Our approach uses short goal-conditioned policies organized hierarchically, with Monte Carlo Tree Search (MCTS) planning using high-level actions (HLAs)<n>A single plan-tree, maintained during the agent's lifetime, holds knowledge about goal achievement.
  arXiv  Detail & Related papers  (2025-01-03T09:37:54Z)
• Generalization of Compositional Tasks with Logical Specification via Implicit Planning [14.46490764849977]
  We introduce a new hierarchical RL framework that enhances the efficiency and optimality of task generalization. At the high level, we present an implicit planner specifically designed for generalizing compositional tasks. It learns a latent transition model and performs planning in the latent space by using a graph neural network (GNN)
  arXiv  Detail & Related papers  (2024-10-13T00:57:10Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Planning with Multi-Constraints via Collaborative Language Agents [13.550774629515843]
  This paper introduces Planning with Multi-Constraints (PMC), a zero-shot methodology for collaborative multi-agent systems.<n>PMC simplifies complex task planning with constraints by decomposing it into a hierarchy of subordinate tasks.<n>PMC achieved an average 42.68% success rate on TravelPlanner, significantly higher than GPT-4 (2.92%), and outperforming GPT-4 with ReAct on API-Bank by 13.64%.
  arXiv  Detail & Related papers  (2024-05-26T10:33:17Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [68.29746557968107]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.<n> Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL [80.10358123795946]
  We develop a framework for building multi-turn RL algorithms for fine-tuning large language models. Our framework adopts a hierarchical RL approach and runs two RL algorithms in parallel. Empirically, we find that ArCHer significantly improves efficiency and performance on agent tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:45:56Z)
• Tree-Planner: Efficient Close-loop Task Planning with Large Language Models [63.06270302774049]
  Tree-Planner reframes task planning with Large Language Models into three distinct phases. Tree-Planner achieves state-of-the-art performance while maintaining high efficiency.
  arXiv  Detail & Related papers  (2023-10-12T17:59:50Z)

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.