Papers with multimodal reasoning benchmarks

6 papers
Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Recent work has shown promise by incorporating pixel-level visual information into the reasoning process, enabling VLMs to access high-resolution visual details during their thought process.
Approach: They propose a framework that dynamically determines necessary pixel-level operations based on the input query.
Outcome: The proposed model achieves 73.4% accuracy on HR-Bench 4K while maintaining a tool usage ratio of only 20.1%, improving accuracy and reducing tool usage by 66.5% compared to the previous methods.
Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing efforts to improve task accuracy or enrich COT generation are lacking in multimodal large language models.
Approach: They propose a Faithful-First Reasoning, Planning, and Acting framework that evaluates faithfulness of intermediate reasoning and uses it to plan and execute faithfulness-aware actions during inference.
Outcome: The proposed framework improves perceptual faithfulness by up to 24% over prompt-based and tool-augmented reasoning frameworks without degrading task accuracy.
DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models (MLLMs) have made rapid progress in perception and alignment, but their reasoning ability often lags behind strong text-only LLMs.
Approach: They propose a method that transfers reasoning knowledge in the gradient space while preserving multimodal alignment.
Outcome: Experiments on multimodal reasoning benchmarks show that DRIFT outperforms naive merging and standard SFT.
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models (MLLMs) have advanced from perception tasks to complex multi-step reasoning.
Approach: They propose a framework that integrates reinforcement learning with verifiable rewards with process-level supervision through automatically collected rubric-based generative rewards.
Outcome: The proposed framework achieves state-of-the-art performance on six multimodal reasoning benchmarks and significantly improves reasoning faithfulness in dedicated evaluations.
Interleaved Latent Visual Reasoning with Selective Perceptual Modeling (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to interleaved reasoning are limited by the cost of re-encoding pixel-dense images.
Approach: They propose a framework that unifies dynamic state evolution with precise perceptual modeling.
Outcome: The proposed framework outperforms existing approaches on multimodal reasoning benchmarks.
IREASONER: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing self-evolving frameworks mainly reward final outcomes, leaving intermediate reasoning weakly constrained despite its importance for visually grounded decision making.
Approach: They propose a framework that improves an LMM’s implicit reasoning by explicitly eliciting chain-of-thought (CoT) and rewarding its internal agreement.
Outcome: The proposed framework yields +2.1 points across diverse multimodal reasoning benchmarks under fully unsupervised post-training.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations