Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2605.13277v1
• Date: Wed, 13 May 2026 09:54:31 GMT
• Title: Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
• Abstract summary: We reformulate multimodal evidence selection from an information-theoretic perspective by defining evidence utility as the information gain induced on a model's output distribution.<n>We propose a training-free, surrogate-accelerated framework that efficiently estimates evidence utility using lightweight multimodal models.
• Score: 14.767796866137187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual evidence selection is a critical component of multimodal retrieval-augmented generation (RAG), yet existing methods typically rely on semantic relevance or surface-level similarity, which are often misaligned with the actual utility of visual evidence for downstream reasoning. We reformulate multimodal evidence selection from an information-theoretic perspective by defining evidence utility as the information gain induced on a model's output distribution. To overcome the intractability of answer-space optimization, we introduce a latent notion of evidence helpfulness and theoretically show that, under mild assumptions, ranking evidence by information gain on this latent variable is equivalent to answer-space utility. We further propose a training-free, surrogate-accelerated framework that efficiently estimates evidence utility using lightweight multimodal models. Experiments on MRAG-Bench and Visual-RAG across multiple model families demonstrate that our method consistently outperforms state-of-the-art RAG baselines while achieving substantial reductions in computational cost.

Related papers

• HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research [52.87128503345243]
  We introduce HiEviDR-Bench, a benchmark for evaluating Hierarchical Evidence Aggregation in Deep Research.<n>HiEviDR-Bench represents each instance with an explicit evidence graph that captures evidence selection, cross-source linking, and aggregation.<n>We develop a traceability-oriented evaluation framework with five dimensions: report quality, evidence traceability, citation accuracy, claim verification, and answer correctness.
  arXiv  Detail & Related papers  (2026-07-27T23:50:46Z)
• MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering [73.47440561592556]
  We introduce MultAttnAttrib, a training-free attribution-generation method.<n>We show that MultAttnAttrib consistently outperforms a variety of attribution-generation methods.<n>Our method produces attributions at up to one-seventh of the direct inference latency compared to prompting.
  arXiv  Detail & Related papers  (2026-07-01T19:29:19Z)
• Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking [22.2668894000344]
  Multimodal Entity Linking (MEL) is a fundamental task in data management that maps ambiguous mentions with diverse modalities to the multimodal entities in a knowledge base.<n>We propose MSR-MEL, a Multi-perspective Evidence Synthesis and Reasoning framework with Large Language Models (LLMs) for unsupervised MEL.
  arXiv  Detail & Related papers  (2026-04-22T07:30:16Z)
• MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation [36.73029890123542]
  MASS-RAG is a multi-agent synthesis approach to retrieval-augmented generation.<n>It applies distinct agents for evidence summarization, evidence extraction, and reasoning over retrieved documents.<n>It combines their outputs through a dedicated synthesis stage to produce the final answer.
  arXiv  Detail & Related papers  (2026-04-20T17:00:38Z)
• POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch [84.73366911912512]
  We introduce Agentic Seeding, a dedicated phase designed to weave the precursors necessary for eliciting agentic behaviors.<n>We propose V-Fold, an adaptive history-aware compression scheme that preserves recent dialogue turns in high fidelity while folding historical context into the visual space via rendering.<n>We develop POINTS-Seeker-8B, a state-of-the-art multimodal agentic search model that consistently outperforms existing models across six diverse benchmarks.
  arXiv  Detail & Related papers  (2026-04-15T16:09:37Z)
• Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization [89.68681087743876]
  Multimodal Large Language Models (MLLMs) have incentivized models to think with images'' by actively invoking visual tools during multi-turn reasoning.<n>The common Reinforcement Learning practice of relying on outcome-based rewards ignores the fact that textual plausibility often masks executive failure.<n>We introduce Multimodal Agentic Policy Optimization (MAPO), bridging the gap between textual reasoning and visual actions generated by models within their Multimodal Chain-of-Thought.
  arXiv  Detail & Related papers  (2026-04-08T07:48:07Z)
• V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval [32.5242219186118]
  We propose V-Retrver, an evidence-driven retrieval framework that reformulates multimodal retrieval as an agentic reasoning process grounded in visual inspection.<n>V-Retrver enables an MLLM to selectively acquire visual evidence during reasoning via external visual tools, performing a multimodal interleaved reasoning process that alternates between hypothesis generation and targeted visual verification.
  arXiv  Detail & Related papers  (2026-02-05T18:59:21Z)
• BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation [33.53566598271416]
  BayesRAG is a novel multimodal retrieval framework grounded in Bayesian inference and Dempster-Shafer evidence theory.<n>We show that BayesRAG significantly outperforms state-of-the-art (SOTA) methods on challenging multimodal benchmarks.
  arXiv  Detail & Related papers  (2026-01-12T08:53:14Z)
• ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning [103.7657839292775]
  ARM-Thinker is an Agentic multimodal Reward Model that autonomously invokes external tools to ground judgments in verifiable evidence.<n>We train ARM-Thinker with multi-stage reinforcement learning, jointly optimizing tool-calling decisions and judgment accuracy.<n>Our results demonstrate that agentic capabilities significantly enhance both accuracy and interpretability of reward models.
  arXiv  Detail & Related papers  (2025-12-04T18:59:52Z)
• Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning [49.3242278912771]
  We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning) The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs. It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-31T14:23:49Z)
• Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning [80.44084021062105]
  We propose a novel latent partial causal model for multimodal data, featuring two latent coupled variables, connected by an undirected edge, to represent the transfer of knowledge across modalities.<n>Under specific statistical assumptions, we establish an identifiability result, demonstrating that representations learned by multimodal contrastive learning correspond to the latent coupled variables up to a trivial transformation.<n>Experiments on a pre-trained CLIP model embodies disentangled representations, enabling few-shot learning and improving domain generalization across diverse real-world datasets.
  arXiv  Detail & Related papers  (2024-02-09T07:18:06Z)
• Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering [20.59485758381809]
  Current multimodal retrieval question-answering models face two main challenges. utilizing compressed evidence features as input to the model results in the loss of fine-grained information within the evidence. We propose a two-stage framework for evidence retrieval and question-answering to alleviate these issues.
  arXiv  Detail & Related papers  (2023-10-15T01:18:39Z)

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.