Pith. sign in

REVIEW 21 cited by

Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.06805 v2 pith:TQLEAYAC submitted 2024-01-10 cs.CL cs.AI

Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning

classification cs.CL cs.AI
keywords mllmsmultimodalreasoninglanguagelargemodelssurveyabilities
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Strong Artificial Intelligence (Strong AI) or Artificial General Intelligence (AGI) with abstract reasoning ability is the goal of next-generation AI. Recent advancements in Large Language Models (LLMs), along with the emerging field of Multimodal Large Language Models (MLLMs), have demonstrated impressive capabilities across a wide range of multimodal tasks and applications. Particularly, various MLLMs, each with distinct model architectures, training data, and training stages, have been evaluated across a broad range of MLLM benchmarks. These studies have, to varying degrees, revealed different aspects of the current capabilities of MLLMs. However, the reasoning abilities of MLLMs have not been systematically investigated. In this survey, we comprehensively review the existing evaluation protocols of multimodal reasoning, categorize and illustrate the frontiers of MLLMs, introduce recent trends in applications of MLLMs on reasoning-intensive tasks, and finally discuss current practices and future directions. We believe our survey establishes a solid base and sheds light on this important topic, multimodal reasoning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 21 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding

    cs.CV 2026-04 unverdicted novelty 8.0

    3D-VCD reduces hallucinations in 3D-LLM embodied agents by contrasting predictions from original and distorted 3D scene representations at inference time.

  2. MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs

    cs.CV 2025-11 unverdicted novelty 8.0

    MVI-Bench supplies the first taxonomy and dataset focused on misleading visual inputs to measure LVLM robustness, with tests on 18 models revealing clear weaknesses.

  3. ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection

    cs.CL 2024-10 unverdicted novelty 8.0

    ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.

  4. Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning

    cs.CV 2025-07 unverdicted novelty 7.0

    Presents Reason50K dataset and ReasonBrain framework for hypothetical instruction-based image editing that requires physical, temporal, causal, and story reasoning.

  5. Investigating Adversarial Robustness of Multi-modal Large Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    Robust vision encoders from multimodal adversarial pretraining transfer to MLLMs and deliver large gains in adversarial captioning and VQA performance, while test-time stochastic transformations provide an effective b...

  6. Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models

    cs.CV 2026-05 conditional novelty 6.0

    SPpruner reduces visual tokens in VLMs via focus identification followed by context-aware scanning, retaining 22.2% tokens for 2.53x speedup on Qwen2.5-VL with negligible accuracy loss.

  7. GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 6.0

    GRIP-VLM applies group-relative policy optimization via reinforcement learning to prune visual tokens in VLMs, yielding up to 15% inference speedup at matched accuracy over prior methods.

  8. Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training

    cs.CV 2026-05 unverdicted novelty 6.0

    VISTA uses prefix resampling and a vision-aware attention score to address data imbalance and language prior bias in self-improvement training of MLLMs, yielding up to 13.66% gains on reasoning tasks.

  9. Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design

    cs.AI 2026-04 unverdicted novelty 6.0

    Mol-Debate applies multi-agent debate in an iterative loop with perspective orchestration to achieve state-of-the-art text-guided molecular design, scoring 59.82% exact match on ChEBI-20 and 50.52% weighted success on...

  10. All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding

    cs.CV 2026-04 unverdicted novelty 6.0

    A unified synthetic data generation pipeline produces unlimited annotated multimodal video data across multiple tasks, enabling models trained mostly on synthetic data to generalize effectively to real-world video und...

  11. Learning Preference-Based Objectives from Clinical Narratives for Dynamic Sepsis Treatment

    cs.AI 2026-04 unverdicted novelty 6.0

    CN-PR learns reward functions from LLM-derived preferences over clinical trajectories to improve RL policies for sequential treatment decisions, showing correlation with quality scores and better recovery outcomes.

  12. Learning Preference-Based Objectives from Clinical Narratives for Dynamic Sepsis Treatment

    cs.AI 2026-04 unverdicted novelty 6.0

    CN-PR learns offline-RL rewards for dynamic sepsis treatment from LLM-scored discharge-summary preferences, improving recovery metrics while matching mortality baselines.

  13. Dual Tuning for Reasoning Efficacy-Driven Data Curation in Multimodal LLM Training

    cs.CL 2026-02 unverdicted novelty 6.0

    Dual Tuning is a data curation method that jointly scores training examples for benefit and for reasoning-gain to choose between reasoning and direct-answer post-training modes for multimodal LLMs.

  14. PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking

    cs.CR 2025-07 unverdicted novelty 6.0

    PRISM decomposes harmful instructions into benign visual gadgets and directs LVLMs via prompts to compose them through reasoning into harmful outputs, achieving ASR over 0.90 on SafeBench.

  15. MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems

    cs.CV 2025-03 unverdicted novelty 6.0

    MathFlow decouples perception and inference stages in MLLMs for visual math, with a dedicated perception model delivering gains on the FlowVerse benchmark when paired with existing reasoners.

  16. LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

    cs.CL 2025-03 unverdicted novelty 6.0

    A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.

  17. SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

    cs.CV 2026-06 unverdicted novelty 5.0

    SingGuard introduces a policy-adaptive multimodal LLM guardrail with dynamic reasoning regimes and SingGuard-Bench, reporting SOTA F1 scores across 35 datasets and improved policy-following accuracy under runtime shifts.

  18. SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

    cs.CV 2026-06 unverdicted novelty 5.0

    SingGuard presents a policy-adaptive multimodal LLM guardrail family with hybrid reasoning regimes and a new benchmark of 56,340 examples, claiming SOTA F1 across 35 datasets and improved policy adherence under runtim...

  19. Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs

    cs.CL 2026-04 unverdicted novelty 5.0

    DLR is a new reinforced latent reasoning method for VLMs that decomposes queries, uses continuous visual latents, and outperforms text-only and multimodal CoT baselines on vision-centric benchmarks with better interpr...

  20. Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoning

    cs.CV 2026-05 unverdicted novelty 4.0

    Mags-RL uses agentic RL and a super-resolution agent for two-round reasoning in MLLMs, claiming gains on VSR, TallyQA, and GQA with a curriculum needing only 40 samples.

  21. Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning

    cs.CL 2025-02 unverdicted novelty 2.0

    Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.