Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance

• URL: http://arxiv.org/abs/2605.31003v1
• Date: Fri, 29 May 2026 08:36:08 GMT
• Title: Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance
• Abstract summary: We present Graph-GRPO, a graph-structured extension of GRPO for relevance reasoning.<n>It propagates outcome-level rewards over the graph to derive step-level credit signals.<n>We also introduce a main-loss-driven controller that adaptively adjusts edge-wise credit-propagation coefficients.
• Score: 7.682863634260091
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Search relevance modeling is a core task in e-commerce search systems, assessing how well a user query matches candidate products. Rather than relying on a single holistic matching signal, relevance judgment often requires structured reasoning over query understanding, product understanding, and facet-level matching. With large language models (LLMs), this process is increasingly formulated as chain-of-thought (CoT) reasoning and optimized with reinforcement learning (RL). However, existing RL methods mainly rely on outcome-level rewards and treat the entire reasoning chain as a single optimization unit. This makes it difficult to distinguish faulty reasoning steps from correct intermediate ones, leading to misaligned credit assignment. Although process-reward methods provide denser supervision, they often treat reasoning steps independently and ignore dependency-driven error propagation, making responsibility attribution difficult and limiting the optimization of structured relevance reasoning. We propose Graph-GRPO, a graph-structured extension of GRPO for multi-component relevance reasoning. Graph-GRPO constructs a relevance reasoning dependency graph, where CoT steps are modeled as nodes and their logical dependencies as edges. It propagates outcome-level rewards over the graph to derive step-level credit signals, enabling more accurate fine-grained credit assignment. We further introduce a main-loss-driven controller that adaptively adjusts edge-wise credit-propagation coefficients. Together with CoT random masking for supervised policy initialization and graph-node-based multi-head distillation, we build a trainable and deployable framework for generative relevance modeling. Extensive offline evaluations and online A/B tests on a leading e-commerce platform demonstrate that the Graph-GRPO-based framework improves relevance classification metrics and key engagement metrics.

Related papers

• Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry [105.89493240787861]
  We introduce credit-addressable reasoning, in which semantic units exposed during inference also define where learning compares alternatives and assigns credit.<n>We instantiate this principle with Code-CoT, which represents visual relations as line-addressable executable code, and organizes reasoning into typed events.<n>Across nine geometry benchmarks, CE-GRPO achieves an average accuracy of 76.04, outperforming Qwen3-VL-8B and trajectory-level GRPO by $8.09$ and 3.43 points, respectively.
  arXiv  Detail & Related papers  (2026-08-31T08:44:36Z)
• Agentic Planning with Reasoning for Image Styling via Offline RL [66.10749901925941]
  Direct prompt-based editing fails on complex transformations because vague and subjective prompts often require nuanced understanding of what should be changed in the image.<n>We present a tool-based agentic RL post-training framework that addresses this through structured planning with chain-of-thought reasoning.
  arXiv  Detail & Related papers  (2026-03-07T11:14:37Z)
• Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization [7.961090665261694]
  We propose Graph-GRPO, a novel topology optimization framework that integrates Group Relative Policy Optimization.<n>By normalizing rewards across the sampled group, our method effectively mitigates the noise derived from task difficulty variance and enables fine-grained credit assignment.
  arXiv  Detail & Related papers  (2026-03-03T07:45:40Z)
• From Flat to Structural: Enhancing Automated Short Answer Grading with GraphRAG [8.449978933501965]
  We introduce a Graph Retrieval-Augmented Generation (GraphRAG) framework that organizes reference materials into a structured knowledge graph.<n>Our methodology employs a dual-phase pipeline: utilizing Microsoft GraphRAG for high-fidelity graph construction and the HippoRAG neurosymbolic algorithm.
  arXiv  Detail & Related papers  (2026-02-28T04:44:06Z)
• ProGraph-R1: Progress-aware Reinforcement Learning for Graph Retrieval Augmented Generation [37.11787010202267]
  We propose ProGraph-R1, a progress-aware agentic framework for graph-based retrieval and multi-step reasoning.<n>ProGraph-R1 introduces a structure-aware hypergraph retrieval mechanism that jointly considers semantic relevance and graph connectivity.<n> Experiments on multi-hop question answering benchmarks demonstrate that ProGraph-R1 consistently improves reasoning accuracy and generation quality over existing GraphRAG methods.
  arXiv  Detail & Related papers  (2026-01-25T08:58:44Z)
• Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models [45.28250076657801]
  Long Chain-of-Thought (LCoT) has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Despite RLVR-based optimization, existing methods still suffer from coarse-grained supervision, reward hacking, high training costs, and poor generalization.<n>We propose the Graph Reasoning Paradigm (GRP), which realizes structured and symbolic reasoning, implemented via graph-structured representations with step-level cognitive labels.
  arXiv  Detail & Related papers  (2026-01-19T12:23:00Z)
• TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG [71.06073770344732]
  Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval.<n>We present TreePS-RAG, an online, tree-based RL framework for agentic RAG that enables step-wise credit assignment while retaining outcome-only rewards.
  arXiv  Detail & Related papers  (2026-01-11T14:07:30Z)
• RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning [69.87510139069218]
  Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs)<n>Recent progress has advanced text-based RAG to multi-turn reasoning through Reinforcement Learning (RL)<n>We introduce model, an RL-based framework that enables LLMs to perform multi-turn and adaptive graph-text hybrid RAG.
  arXiv  Detail & Related papers  (2025-12-10T10:05:31Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge [88.82814893945077]
  Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge.<n>Recent graph-enhanced RAG (GraphRAG) attempts to bridge this gap by constructing tailored graphs and enabling LLMs to reason on them.<n>G-reasoner is a unified framework that integrates graph and language foundation models for reasoning over diverse graph-structured knowledge.
  arXiv  Detail & Related papers  (2025-09-29T04:38:12Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures [16.867592142212203]
  Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge.<n>Retrieval-augmented generation (RAG) addresses this by retrieving query-relevant contexts from knowledge bases to support LLM reasoning.<n>Existing Graph-based RAG methods rely on a costly process to transform the corpus into a graph, introducing overwhelming token cost and update latency.<n>We propose LogicRAG that dynamically extracts reasoning structures at inference time to guide adaptive retrieval without any pre-built graph.
  arXiv  Detail & Related papers  (2025-08-08T08:07:40Z)
• Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures [0.0]
  We introduce Adaptive Graph of Thoughts (AGoT), a dynamic, graph-based inference framework.<n>AGoT enhances Large Language Models (LLMs) reasoning solely at test time.<n>We validate our approach on diverse benchmarks spanning multi-hop retrieval, scientific reasoning, and mathematical problem-solving.
  arXiv  Detail & Related papers  (2025-02-07T16:54:19Z)

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.