Skip to content
← Back to explorer

Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation

Chunyi Peng, Zhipeng Xu, Zhenghao Liu, Yishan Li, Yukun Yan, Shuo Wang, Yu Gu, Minghe Yu, Ge Yu, Maosong Sun · May 28, 2025 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Apr 6, 2026, 12:52 PM

Recent

Extraction refreshed

Apr 9, 2026, 6:05 PM

Fresh

Extraction source

Persisted extraction

Confidence 0.25

Abstract

Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge. However, existing methods typically adhere to rigid retrieval paradigms by mimicking fixed retrieval trajectories and thus fail to fully exploit the knowledge of different retrieval experts through dynamic interaction based on the model's knowledge needs or evolving reasoning states. To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation. Specifically, MoRE learns to dynamically determine which expert to engage with, conditioned on the evolving reasoning state. To effectively train this capability, we propose Stepwise Group Relative Policy Optimization (Step-GRPO), which goes beyond sparse outcome-based supervision by encouraging MLLMs to interact with multiple retrieval experts and synthesize fine-grained rewards, thereby teaching the MLLM to fully coordinate all experts when answering a given query. Experimental results on diverse open-domain QA benchmarks demonstrate the effectiveness of MoRE, achieving average performance gains of over 7% compared to competitive baselines. Notably, MoRE exhibits strong adaptability by dynamically coordinating heterogeneous experts to precisely locate relevant information, validating its capability for robust, reasoning-driven expert collaboration. All codes and data are released on https://github.com/OpenBMB/MoRE.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.25 (below strong-reference threshold).
  • No explicit evaluation mode was extracted from available metadata.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Persisted extraction missing

Validate eval design from full paper text.

Evidence snippet: Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge.

Benchmarks / Datasets

partial

Mixture Of Retrieval

Confidence: Low Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation.

Reported Metrics

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No metric anchors detected.

Evidence snippet: Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge.

Rater Population

partial

Domain Experts

Confidence: Low Source: Persisted extraction evidenced

Helpful for staffing comparability.

Evidence snippet: However, existing methods typically adhere to rigid retrieval paradigms by mimicking fixed retrieval trajectories and thus fail to fully exploit the knowledge of different retrieval experts through dynamic interaction based on the model's knowledge needs or evolving reasoning states.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Domain Experts
  • Unit of annotation: Unknown
  • Expertise required: General
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.25
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

mixture-of-retrieval

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Deterministic synthesis

To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation. HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Apr 9, 2026, 6:05 PM · Grounded in abstract + metadata only

Key Takeaways

  • To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for…
  • To effectively train this capability, we propose Stepwise Group Relative Policy Optimization (Step-GRPO), which goes beyond sparse outcome-based supervision by encouraging MLLMs…
  • Experimental results on diverse open-domain QA benchmarks demonstrate the effectiveness of MoRE, achieving average performance gains of over 7% compared to competitive baselines.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Cross-check benchmark overlap: mixture-of-retrieval.
  • Verify metric definitions before comparing against your eval pipeline.

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation.
  • To effectively train this capability, we propose Stepwise Group Relative Policy Optimization (Step-GRPO), which goes beyond sparse outcome-based supervision by encouraging MLLMs to interact with multiple retrieval experts and synthesize…
  • Experimental results on diverse open-domain QA benchmarks demonstrate the effectiveness of MoRE, achieving average performance gains of over 7% compared to competitive baselines.

Why It Matters For Eval

  • Experimental results on diverse open-domain QA benchmarks demonstrate the effectiveness of MoRE, achieving average performance gains of over 7% compared to competitive baselines.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Gap: Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: mixture-of-retrieval

  • Gap: Metric reporting is present

    No metric terms extracted.

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote