Reasoning Like Humans: Enhancing Multi-Image Reasoning Via Cognition-Inspired Meta-Action Framework

ICLR 2026 Conference Submission20081 Authors

Keywords: Multimodal Large Language Models, Multi-image Reasoning

Abstract:

While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical information across image sets. Inspired by human cognitive processes, we propose the Cognition-Inspired Meta-Action Framework (CINEMA), a novel approach that decomposes multi-image reasoning into five structured meta-actions: Global, Focus, Hint, Think, and Answer which explicitly modeling the sequential cognitive steps humans naturally employ.
For cold-start training, we introduce a Retrieval-Based Tree Sampling strategy that generates high-quality meta-action trajectories to bootstrap the model with reasoning patterns. During reinforcement learning, we adopt a two-stage paradigm: an exploration phase with Diversity-Preserving Policy Optimization (DiPO) to avoid entropy collapse, followed by an annealed exploitation phase with DAPO to to gradually strengthen exploitation. To train our model,We construct a dataset of 57k cold-start and 58k reinforcement learning instances spanning multi-image, multi-frame, and single-image tasks. We conduct extensive evaluations on multi-image reasoning benchmarks, video understanding benchmarks, and single-image benchmarks, achieving competitive state-of-the-art performance on several key benchmarks. Our model surpasses GPT-4o on the MUIR and MVMath benchmarks and notably outperforms specialized video reasoning models on video understanding benchmarks, demonstrating the effectiveness and generalizability of our human cognition-inspired reasoning framework.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 20081