Embodied planning is dedicated to the goal of building agents capable of perceiving, reasoning, and executing long-horizon tasks in physical environments. However, existing embodied benchmarks predominantly focus on single-agent execution or restricted multi-agent settings, leaving long-horizon tasks that involve complex inter-agent dependencies largely underexplored despite their prevalence in real-world embodied scenarios. To address this gap, we introduce CoEmbod, the first realistic 3D simulated embodied benchmark for long-horizon multi-agent embodied cooperation with diverse inter-agent dependencies. CoEmbod contains 155 expert-curated tasks across 40 scenes and 10845 objects, covering three cooperation regimes: spatial distribution, parallel constraint, and failure recovery. These regimes cover a broad spectrum of cooperative requirements, ranging from distributed task allocation to synchronized execution and assisted failure recovery. CoEmbod further provides a process-level evaluation framework with Budgeted Cooperative Success (BCS), which jointly measures goal completion, cooperation fidelity, and execution efficiency. Experiments reveal that even the leading LMM powering a well-established agentic workflow achieves only 20.23% success, highlighting the difficulty of long-horizon multi-agent cooperation with diverse inter-agent dependencies in complex embodied environments.

Referring expression grounding is a core problem in visual grounding and is widely used as a diagnostic of spatial grounding and reasoning in vision–language models, yet most prior work focuses on natural images. In contrast, existing chart referring expression grounding-related benchmarks remain limited: (1) they largely adopt bounding boxes, constraining localization precision for fine chart elements; (2) they mostly assume one and two referred target instances, failing to handle multi-instance target references; (3) the language expressions over-rely on textual cues or data-ranking clues in the chart; (4) they cover only a narrow range of chart types. To address these issues, we introduce a chart referring expression grounding benchmark that first systematically supports multiple localization formats, multiple referred targets, diverse grounding cues and diverse chart types. Results across representative multi-modal large models reveal a significant performance gap. We further introduce an LLM-free synthesis pipeline that exploits the inherent alignment between matplotlib internal artist hierarchy and rendered chart primitives to derive pixel-accurate, multi-granularity instance segmentation masks. We train an instance segmentation model with the synthesized masks and integrate it into a general-purpose multi-modal grounding framework. The resulting system consistently outperforms baselines on our benchmark and generalizes well to a ChartQA-derived real-chart grounding benchmark.

Vision-Language-Action (VLA) models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understood. In this work, We present the first systematic multilingual evaluation of VLA models by translating the LIBERO benchmark into ten languages, revealing severe performance degradation under non-English instructions, with success rates dropping by 30–50%. Through fine-grained analysis of task executions, we find that language influence is highly non-uniform across steps: certain steps exhibit strong language dependence and dominate overall task failure, while others are largely language-agnostic. Based on this insight, we propose a step-wise inference-time intervention that aligns representations according to step language sensitivity, substantially improving performance under linguistic variation. Our results indicate that language robustness in VLA models is fundamentally a step-wise control problem, highlighting the importance of temporally structured analysis for reliable embodied agents.

To tackle complex tasks in real-world scenarios, more researchers are focusing on Omni-MLLMs, which aim to achieve omni-modal understanding and generation. Beyond the constraints of any specific non-linguistic modality, Omni-MLLMs map various non-linguistic modalities into the embedding space of LLMs and enable the interaction and understanding of arbitrary combinations of modalities within a single model. In this paper, we systematically investigate relevant research and provide a comprehensive survey of Omni-MLLMs. Specifically, we first explain the four core components of Omni-MLLMs for unified multi-modal modeling with a meticulous taxonomy that offers novel perspectives. Then, we introduce the effective integration achieved through two-stage training and discuss the corresponding datasets as well as evaluation. Furthermore, we summarize the main challenges of current Omni-MLLMs and outline future directions. We hope this paper serves as an introduction for beginners and promotes the advancement of related research. Resources have been made publicly availableat https://github.com/threegold116/Awesome-Omni-MLLMs.

Large Multimodal Models (LMMs) have recently demonstrated impressive performance on general video comprehension benchmarks. Nevertheless, for broader applications, the robustness of their temporal analysis capability needs to be thoroughly investigated yet predominantly ignored. Motivated by this, we propose a novel temporal robustness benchmark (TemRobBench), which introduces temporal inconsistency perturbations separately at the visual and textual modalities to assess the robustness of models. We evaluate 16 mainstream LMMs and find that they exhibit over-reliance on prior knowledge and textual context in adversarial environments, while ignoring the actual temporal dynamics in the video. To mitigate this issue, we design panoramic direct preference optimization (PanoDPO), which encourages LMMs to incorporate both visual and linguistic feature preferences simultaneously. Experimental results show that PanoDPO can effectively enhance the model’s robustness and reliability in temporal analysis.