Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning

• URL: http://arxiv.org/abs/2606.22995v1
• Date: Mon, 22 Jun 2026 08:12:47 GMT
• Title: Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
• Abstract summary: Group-Graph Policy Optimization (G2PO) is a novel group-based Reinforcement Learning algorithm tailored for multi-turn agentic tasks.<n>G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.
• Score: 85.02566758103008
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, recent agentic RL frameworks have shifted from trajectory-level to step-level training. However, long-horizon agentic RL suffers from severe reward sparsity and delay, as feedback is often deferred for dozens of interaction steps. While existing step-level frameworks refine training granularity, their credit assignment remains coarse-grained and still treats agent exploration as isolated, linear trajectories. This oversimplified perspective ignores the inherent graph structure of state transitions, leading to high-variance state-value estimation and myopic, localized credit assignment. To overcome these critical bottlenecks, we propose Group-Graph Policy Optimization (G2PO), a novel group-based RL algorithm tailored for multi-turn agentic tasks. G2PO explicitly transforms linear interaction trajectories into a global state-transition graph. By aggregating identical observations across different trajectories, we introduce group-aggregation state-value estimation that reduces sampling variance and trajectory-dependent bias. Furthermore, we redefine agent actions as transitions between state nodes and propose an edge-centric advantage estimation strategy. By globally standardizing Temporal Difference (TD) errors across the entire graph, G2PO explicitly identifies and prioritizes critical transitions that drive absolute task progress. Extensive experiments on representative long-horizon benchmarks-WebShop, ALFWorld, and AppWorld-demonstrate that G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.

Related papers

• Granularity-Adaptive Credit Assignment for Long-Horizon LLM Agent Reinforcement Learning [7.885980895039013]
  We argue that the right resolution is state-dependent, and propose GACA, a critic-free estimator whose granularity follows an uncertainty-based criticality proxy.<n>GACA scores every step by the negative log-likelihood its own rollout already records, then blends the two advantages with a per-step weight that grows with that score.<n>On ALFWorld and WebShop, GACA improves task success over GRPO and GiGPO at both 1.5B and 7B scales.
  arXiv  Detail & Related papers  (2026-09-11T04:19:44Z)
• AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning [58.76655851910778]
  AgentOPSD is a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning.<n>We evaluate AgentOPSD on ALFWorld, WebShop, and Search-QA using Qwen2.5 models at two scales (3B and 7B)
  arXiv  Detail & Related papers  (2026-08-06T13:00:59Z)
• Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning [5.952158244195666]
  We propose ProGPO, a learned-critic-free method for context-consistent step-level learning.<n>We evaluate ProGPO on two challenging agentic tasks, ALFWorld and WebShop, with Qwen2.5-1.5B-Instruct.
  arXiv  Detail & Related papers  (2026-07-05T11:41:46Z)
• Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning [30.228760269449072]
  Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs)<n>We propose Graph-based Group Policy Optimization (GraphGPO), which aggregates all rollout trajectories into a unified state-transition graph.<n>It estimates the distance from each state to the task goal using the global information encoded in the graph.<n>Finally, GraphGPO assigns credit to each edge by estimating a graph-based advantage, based on how much the transition reduces the distance to the task goal.
  arXiv  Detail & Related papers  (2026-05-26T08:23:34Z)
• What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents [70.6980022118038]
  Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging.<n>Existing methods rely on trajectory-level rewards or proxy signals, without fully leveraging per-step environmental feedback.<n>We introduce SERL, a selective environment-reweighted learning framework.
  arXiv  Detail & Related papers  (2026-05-19T07:00:55Z)
• GAGPO: Generalized Advantage Grouped Policy Optimization [13.085463559931156]
  We propose a critic-free reinforcement learning method for precise, step-aligned temporal credit assignment.<n>Experiments on ALFWorld and WebShop show that GAGPO outperforms strong reinforcement learning baselines.
  arXiv  Detail & Related papers  (2026-05-13T09:10:03Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment [61.80228667422234]
  VGPO redefines value estimation across both temporal and group dimensions.<n>It transforms the sparse terminal reward into dense, process-aware value estimates.<n>It replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal.
  arXiv  Detail & Related papers  (2025-12-13T16:31:26Z)
• 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)
• TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization [12.061547251822326]
  Trajectory-based Group Relative Policy Optimization (TGRPO) is an online RL-based training framework for Visual-Language-Action (VLA) models.<n>We show that TGRPO achieves an average success rate of 80.7%, which is 4.2% higher than that of Supervised Fine-Tuning (SFT) and outperforms other representative RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-06-10T04:27:49Z)
• Group-in-Group Policy Optimization for LLM Agent Training [17.243181792126563]
  Group-in-Group Policy Optimization (GiGPO) is a novel RL algorithm that achieves fine-grained credit assignment for LLM agents.<n>We evaluate GiGPO on challenging agent benchmarks, including ALFWorld and WebShop, as well as tool-integrated reasoning on search-augmented QA tasks.
  arXiv  Detail & Related papers  (2025-05-16T08:26:59Z)

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.