ICEGR: An Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search

• URL: http://arxiv.org/abs/2608.29652v2
• Date: Wed, 02 Sep 2026 11:51:23 GMT
• Title: ICEGR: An Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search
• Abstract summary: Generative Retrieval (GR) is promising for e-commerce search.<n>Existing methods struggle to maintain query-intent consistency throughout the training pipeline.<n>We propose ICEGR, an Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search.
• Score: 26.387550337217125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Retrieval (GR) is promising for e-commerce search, yet existing methods struggle to maintain query-intent consistency throughout the training pipeline. First, semantic ID (SID) construction based on static product information limits the ability of SIDs to encode product-intent associations. Second, although supervised fine-tuning (SFT) learns product-SID mappings across the catalog, low-exposure products still lack real query-intent supervision because query-to-SID training relies solely on online logs, resulting in poor retrieval performance for these products. Third, business-oriented preference optimization may favor popular or high-value products over those that best match the query intent, weakening query-product relevance. To address these issues, we propose ICEGR, an Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search that integrates query intent consistently throughout the GR training pipeline. ICEGR comprises three components: (1) Intent-Aware SID Construction incorporates query-intent signals into SID construction, enabling SIDs to capture search intent beyond static product information; (2) Synthetic Query-Enhanced Unified SFT unifies multiple SFT tasks under the query-to-SID objective and augments sparse supervision from online logs with synthetic queries, providing complementary query-intent supervision for low-exposure products; and (3) Relevance-Calibrated Preference Optimization integrates query-product relevance and business signals into a margin-adaptive preference objective, preserving query intent while enabling business preference learning. Offline results show that ICEGR improves Recall@20 by 21.7% and NDCG@20 by 26.6% over the baseline. Deployed as an end-to-end generative retrieval pathway in Baidu E-commerce Search, ICEGR achieves relative improvements of 3.52% in CTR, 15.96% in order volume, and 7.53% in GMV in an A/B test.

Related papers

• VARG: Value-Aware and Ranking-Aligned Generative Retrieval for Dynamic E-commerce Search [7.64283018838172]
  VARG is a generative retrieval system for Tmall App search that directly admits generated item candidates to the existing final ranker.<n>Three-stage supervised fine-tuning progressively learns item-to-identifier mappings, query-semantic retrieval, and personalized retrieval.<n>Prefix-GRPO combines gated rewards based on output legality, user behavior, ranker advantage, and search relevance with prefix-aware token weighting to align candidate generation with business value and ranking objectives.
  arXiv  Detail & Related papers  (2026-09-13T12:59:04Z)
• TSGR: Taobao Search Generative Retrieval [32.4338892898415]
  We propose a unified generative retrieval framework that incorporates value awareness into both item representation and candidate ranking.<n>$textbfT$aobao $textbfS$earch $textbfG$enerative $textbfR$etrieval ($textbfTSGR$)<n>$textbfVRM$ that is built upon and jointly optimized with the GR, enabling a single model to seamlessly serve as both retriever and pre-ranker.
  arXiv  Detail & Related papers  (2026-07-21T07:17:43Z)
• Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL [8.046510111008638]
  Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval process into a single end-to-end model.<n>We propose a retrieval framework tailored for real-world recall scenarios, positioning generative retrieval as a recall-stage supplement rather than an end-to-end replacement.
  arXiv  Detail & Related papers  (2026-05-14T06:27:46Z)
• OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework [41.83974943844478]
  Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems.<n>OneSearch, as a representative industrial-scale deployed generative search framework, has brought significant commercial and operational benefits.<n>We propose textbfOneSearch-V2, a latent reasoning enhanced self-distillation generative search framework.
  arXiv  Detail & Related papers  (2026-03-25T15:33:34Z)
• Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage [89.58253972744531]
  Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks like report generation.<n>We investigate whether upstream retrieval metrics can serve as reliable early indicators of the final generated response's information coverage.<n>Our findings demonstrate strong correlations between coverage-based retrieval metrics and nugget coverage in generated responses at both topic and system levels.
  arXiv  Detail & Related papers  (2026-03-09T18:20:20Z)
• 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)
• IntSR: An Integrated Generative Framework for Search and Recommendation [23.773378364635523]
  IntSR is an integrated generative framework for search and recommendation.<n>It integrates these disparate tasks using distinct query modalities.<n>IntSR has been successfully deployed across various scenarios in Amap.
  arXiv  Detail & Related papers  (2025-09-25T13:58:33Z)
• FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets [64.51403245281547]
  FORGE is a benchmark for FOrming semantic identifieR in Generative rEtrieval with industrial datasets.<n>For real-world applications, FORGE introduces an offline pretraining schema that reduces online convergence by half.
  arXiv  Detail & Related papers  (2025-09-25T08:44:22Z)
• OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search [43.94443394870866]
  OneSearch is the first industrial-deployed end-to-end generative framework for e-commerce search.<n>OneSearch reduces operational expenditure by 75.40% and improves Model FLOPs Utilization from 3.26% to 27.32%.<n>The system has been successfully deployed across multiple search scenarios in Kuaishou, serving millions of users.
  arXiv  Detail & Related papers  (2025-09-03T11:50:04Z)
• DeepShop: A Benchmark for Deep Research Shopping Agents [70.03744154560717]
  DeepShop is a benchmark designed to evaluate web agents in complex and realistic online shopping environments.<n>We generate diverse queries across five popular online shopping domains.<n>We propose an automated evaluation framework that assesses agent performance in terms of fine-grained aspects.
  arXiv  Detail & Related papers  (2025-06-03T13:08:17Z)
• EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association [83.4879773429742]
  This paper defines the task of E-commerce Script Planning (EcomScript) as three sequential subtasks.<n>We propose a novel framework that enables the scalable generation of product-enriched scripts by associating products with each step.<n>We construct the very first large-scale EcomScript dataset, EcomScriptBench, which includes 605,229 scripts sourced from 2.4 million products.
  arXiv  Detail & Related papers  (2025-05-21T07:21:38Z)

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.