FUSE : Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendation

• URL: http://arxiv.org/abs/2601.02365v1
• Date: Sat, 15 Nov 2025 07:55:51 GMT
• Title: FUSE : Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendation
• Abstract summary: Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation.<n>FUSE implements seven context budgeting strategies: context compression, chain-of-thought reasoning, mini-shot optimization, retrieval-augmented context, two-stage processing, and zero-shot minimalism.
• Score: 1.3618516245643617
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation. Retrieval quality is pivotal, yet failures can arise at several stages: understanding user intent, choosing content types, finding candidates (recall), or ranking results. Meanwhile, sending and processing images is costly, making naive multimodal approaches impractical. We present FUSE: Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendation. FUSE replaces most raw-image prompting with a compact Grounded Design Representation (GDR): a selection aware JSON of canvas elements (image, text, shape, icon, video, logo), structure, styles, salient colors, and user selection provided by the Planner team. FUSE implements seven context budgeting strategies: comprehensive baseline prompting, context compression, chain-of-thought reasoning, mini-shot optimization, retrieval-augmented context, two-stage processing, and zero-shot minimalism. Finally, a pipeline attribution layer monitors system performance by converting subagent signals into simple checks: intent alignment, content-type/routing sanity, recall health (e.g., zero-hit and top-match strength), and ranking displacement analysis. We evaluate the seven context budgeting variants across 788 evaluation queries from diverse users and design templates (refer Figure 3). Our systematic evaluation reveals that Context Compression achieves optimal performance across all pipeline stages, with 93.3% intent accuracy, 86.8% routing success(with fallbacks), 99.4% recall, and 88.5% NDCG@5. This approach demonstrates that strategic context summarization outperforms both comprehensive and minimal contextualization strategies.

Related papers

• WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents [53.426679066400844]
  We introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery.<n>We develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout.<n>We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image.
  arXiv  Detail & Related papers  (2026-08-28T08:28:43Z)
• Do Composed Image Retrieval Benchmarks Require Multimodal Composition? [86.99911649534795]
  We show that strong performance on Composed Image Retrieval benchmarks is assumed to require multimodal composition.<n>Across four widely used CIR benchmarks and eleven Generalist Multimodal Embedding models, a large fraction of queries can be solved using a single modality.<n>High CIR performance can arise from unimodal signals rather than true multimodal composition.
  arXiv  Detail & Related papers  (2026-05-14T12:56:36Z)
• One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries [0.0]
  We present an agentic AI framework for autonomous multimodal query processing that coordinates specialized tools across text, image, audio, video, and document modalities.<n>A central Supervisor dynamically decomposes user queries, delegates subtasks to modality-appropriate tools.<n>For text-only queries, the framework uses learned routing via RouteLLM, while non-text paths use SLM-assisted modality decomposition.
  arXiv  Detail & Related papers  (2026-03-12T05:02:58Z)
• Seeing Through Words: Controlling Visual Retrieval Quality with Language Models [68.49490036960559]
  We propose a new paradigm of quality-controllable retrieval, which enriches short queries with contextual details while incorporating explicit notions of image quality.<n>Our key idea is to leverage a generative language model as a query completion function, extending underspecified queries into descriptive forms.<n>Our proposed approach significantly improves retrieval results and provides effective quality control, bridging the gap between the expressive capacity of modern VLMs and the underspecified nature of short user queries.
  arXiv  Detail & Related papers  (2026-02-24T18:20:57Z)
• Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding [49.26132236798123]
  Vision Language Models (VLMs) have gradually become a primary approach in document understanding.<n>We propose SLEUTH, a multi agent framework that orchestrates a retriever and four collaborative agents in a coarse to fine process.<n>The framework identifies key textual and visual clues within the retrieved pages, filters for salient visual evidence such as tables and charts, and analyzes the query to devise a reasoning strategy.
  arXiv  Detail & Related papers  (2025-11-28T03:09:40Z)
• Talk, Snap, Complain: Validation-Aware Multimodal Expert Framework for Fine-Grained Customer Grievances [14.30884038757821]
  Existing approaches to complaint analysis largely rely on unimodal, short-form content such as tweets or product reviews.<n>We introduce VALOR, a Validation-Aware Learner with Expert Routing, tailored for this multimodal setting.<n>We evaluate VALOR on a curated multimodal complaint dataset annotated with fine-grained aspect severity and labels.
  arXiv  Detail & Related papers  (2025-11-18T17:29:28Z)
• REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization [16.530984854626038]
  In Taobao e-commerce visual search, user behavior analysis reveals a large proportion of no-click requests.<n>This mismatch between user implicit intent expression and system response defines the User-SearchSys Intent Discrepancy.<n>We propose a novel framework REVISION, which integrates offline reasoning mining with online decision-making and execution.
  arXiv  Detail & Related papers  (2025-10-26T16:15:50Z)
• UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG [82.84014669683863]
  Multimodal retrieval-augmented generation (MM-RAG) is a key approach for applying large language models to real-world knowledge bases.<n>UniDoc-Bench is the first large-scale, realistic benchmark for MM-RAG built from 70k real-world PDF pages.<n>Our experiments show that multimodal text-image fusion RAG systems consistently outperform both unimodal and jointly multimodal embedding-based retrieval.
  arXiv  Detail & Related papers  (2025-10-04T04:30:13Z)
• FitPro: A Zero-Shot Framework for Interactive Text-based Pedestrian Retrieval in Open World [13.089848592467675]
  Text-based Pedestrian Retrieval (TPR) deals with retrieving specific target pedestrians in visual scenes according to natural language descriptions.<n>We propose FitPro, an open-world interactive zero-shot TPR framework with enhanced semantic comprehension and cross-scene adaptability.
  arXiv  Detail & Related papers  (2025-09-20T12:55:18Z)
• CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design [6.830055289299306]
  CAL-RAG is a retrieval-augmented, agentic framework for content-aware layout generation.<n>We implement our framework using LangGraph and evaluate it on a benchmark rich in semantic variability.<n>Results demonstrate that combining retrieval augmentation with agentic multi-step reasoning yields a scalable, interpretable, and high-fidelity solution.
  arXiv  Detail & Related papers  (2025-06-27T06:09:56Z)
• Reward-Agnostic Prompt Optimization for Text-to-Image Diffusion Models [20.292872255460534]
  We introduce RATTPO, a flexible test-time optimization method applicable across various reward scenarios without modification.<n>RATTPO searches for optimized prompts by querying large language models (LLMs) textitwithout requiring reward-specific task descriptions.<n> Empirical results demonstrate the versatility of RATTPO, effectively enhancing user prompts across diverse reward setups.
  arXiv  Detail & Related papers  (2025-06-20T09:02:05Z)
• Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment [53.45813302866466]
  We present ISG, a comprehensive evaluation framework for interleaved text-and-image generation.<n>ISG evaluates responses on four levels of granularity: holistic, structural, block-level, and image-specific.<n>In conjunction with ISG, we introduce a benchmark, ISG-Bench, encompassing 1,150 samples across 8 categories and 21 subcategories.
  arXiv  Detail & Related papers  (2024-11-26T07:55:57Z)
• Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations [67.92679668612858]
  We propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings; and (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its
  arXiv  Detail & Related papers  (2023-06-03T11:50:44Z)
• Automated Concatenation of Embeddings for Structured Prediction [75.44925576268052]
  We propose Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks. We follow strategies in reinforcement learning to optimize the parameters of the controller and compute the reward based on the accuracy of a task model.
  arXiv  Detail & Related papers  (2020-10-10T14:03:20Z)

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.