Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval

• URL: http://arxiv.org/abs/2608.06060v1
• Date: Thu, 06 Aug 2026 14:04:56 GMT
• Title: Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval
• Abstract summary: UniME-R1 is an embedder-adviser framework that learns to reason over initially retrieved candidates.<n>UniME-R1 consistently improves retrieval performance over strong baselines.
• Score: 17.695551248974215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unified multimodal retrieval aims to identify candidates that satisfy complex user intent expressed through heterogeneous inputs. Although Large Vision-Language Model (LVLM)-based retrievers are efficient and scalable, directly encoding raw multimodal inputs often misses fine-grained discriminative cues, leading to confusion among semantically similar candidates. Recent methods mitigate this limitation by generating Chain-of-Thought (CoT) rationales to enrich the query representation. However, such reasoning is typically derived from the query alone: it explains what the query describes, but not what the retriever misunderstands. We argue that effective retrieval reasoning should instead be conditioned on retrieval feedback. Based on this insight, we introduce UniME-R1, an embedder-adviser framework that learns to reason over initially retrieved candidates and generate Retrieval-Centric Chain-of-Thought (RC-CoT). The adviser analyzes candidates individually to identify the discriminative cues confused by the embedder. If the target appears in the initial top-k set, UniME-R1 directly reranks the candidates; otherwise, it generates RC-CoT to refine the retrieval direction and performs full-corpus re-retrieval with a dual-mode embedder. To train the framework, we mine hard negatives to simulate realistic retrieval failures, jointly optimize direct retrieval and RC-CoT-augmented retrieval, and align the adviser with retrieval outcomes through supervised learning and retrieval-oriented reinforcement learning. Extensive experiments on MMEB-V2 and a diverse set of general multimodal retrieval benchmarks demonstrate that UniME-R1 consistently improves retrieval performance over strong baselines.

Related papers

• Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings [18.705254311226565]
  Retrieval-aware Self-Distillation (RASD) constructs privileged guidance from input-supported evidence that distinguishes the positive item from retrieved hard negatives.<n>Retrieval-adaptive Inference (RAI) uses a retrieval confidence head to estimate the remaining retrieval utility of a partial CoT.<n>ReWAM achieves state-of-the-art retrieval performance while delivering up to 5x the inference throughput of competitive explicit-CoT UME methods.
  arXiv  Detail & Related papers  (2026-09-14T09:48:05Z)
• SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerce [4.188658309210585]
  Embedding-based retrieval (EBR) is pivotal in e-commerce search but often struggles with complex semantics.<n>Recent methods often fine-tune large language models (LLMs) for representation learning.<n>We propose Supervised Retrieval-GRPO with Semantic Identifiers (SSR-GRPO)
  arXiv  Detail & Related papers  (2026-08-20T03:19:20Z)
• Generative Universal Multimodal Retrieval with Dual-role Identifiers [1.0981910170846492]
  We propose DrIG, a novel Generative framework for universal multimodal retrieval featuring Dual-role Identifiers.<n>DrIG consistently outperforms state-of-the-art generative multimodal baselines across diverse tasks, while hybrid reranking achieves a favorable efficiency-effectiveness trade-off against strong dense retrievers.
  arXiv  Detail & Related papers  (2026-08-13T09:10:09Z)
• MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG [50.46218163777298]
  Knowledge-based Visual Question Answering (KB-VQA) requires models to retrieve visual entities matching the query image from large-scale encyclopedic knowledge bases and answer related questions.<n>We propose MMAgent-R$2$, an agentic mRAG framework that integrates visual reranking and active rejection as its internal verification mechanism.
  arXiv  Detail & Related papers  (2026-07-08T13:15:39Z)
• Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study [31.167867050243256]
  ThinkGR is a unified framework that interleaves chain-of-thought with docid generation, enabling iterative thinking and retrieval within a single generative process.<n> Experiments on four multi-hop retrieval benchmarks demonstrate that ThinkGR achieves state-of-the-art performance with an average improvement of +6.86%.
  arXiv  Detail & Related papers  (2026-05-21T11:48:35Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs [14.25887925588904]
  We propose a retrieval-augmented framework that combines query-aware neighborhood retrieval with large language model (LLM) chain-of-thought reasoning.<n>ROG decomposes a multi-operator query into a sequence of single-operator sub-queries.<n> Intermediate answer sets are cached and reused across steps, improving consistency on deep reasoning chains.
  arXiv  Detail & Related papers  (2026-02-02T17:45:43Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning [48.01143057928348]
  We present ConvSearch-R1, a framework that eliminates dependency on external rewrite supervision by leveraging reinforcement learning to optimize reformulation directly through retrieval signals.<n>Our novel two-stage approach combines Self-Driven Policy Warm-Up to address the cold-start problem through retrieval-guided self-distillation, followed by Retrieval-Guided Reinforcement Learning with a specially designed rank-incentive reward shaping mechanism that addresses the sparsity issue in conventional retrieval metrics.
  arXiv  Detail & Related papers  (2025-05-21T17:27:42Z)
• iEBAKER: Improved Remote Sensing Image-Text Retrieval Framework via Eliminate Before Align and Keyword Explicit Reasoning [80.44805667907612]
  iEBAKER is an innovative strategy to filter weakly correlated sample pairs.<n>We introduce an alternative Sort After Reversed Retrieval (SAR) strategy.<n>We incorporate a Keyword Explicit Reasoning (KER) module to facilitate the beneficial impact of subtle key concept distinctions.
  arXiv  Detail & Related papers  (2025-04-08T03:40:19Z)
• CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data.<n>Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the score between queries and candidates.<n>We propose a generative cross-modal retrieval framework (CART) based on coarse-to-fine semantic modeling.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• Unified Active Retrieval for Retrieval Augmented Generation [69.63003043712696]
  In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Existing active retrieval methods face two challenges: 1. They usually rely on a single criterion, which struggles with handling various types of instructions. They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated.
  arXiv  Detail & Related papers  (2024-06-18T12:09:02Z)

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.