The current remote sensing image analysis task is increasingly evolving from traditional object recognition to complex intelligence reasoning, which places higher requirements on the model's reasoning ability and the flexibility of tool invocation. T o this end, we propose a new multimodal agent framework, Vision-Interleaved Chain-of-Thought Framework (VICoT), which implements explicit multi-round reasoning by dynamically incorporating visual tools into the chain of thought. Through a stack-based reasoning structure and a modular MCP-compatible tool suite, VICoT enables LLMs to efficiently perform multi-round, interleaved vision-language reasoning tasks with strong generalization and flexibility.W e also propose the Reasoning Stack distillation method to migrate complex Agent behaviors to small, lightweight models, which ensures the reasoning capability while significantly reducing complexity. Experiments on multiple remote sensing benchmarks demonstrate that VICoT significantly outperforms existing SOTA frameworks in reasoning transparency, execution efficiency, and generation quality.

Language models have demonstrated remarkable performance on complex multi-step reasoning tasks. However, their evaluation has been predominantly confined to high-resource languages such as English. In this paper, we introduce a manually translated Bangla multi-step reasoning dataset derived from the English Reveal dataset, featuring both binary and non-binary question types. We conduct a controlled evaluation of English-centric and Bangla-centric multilingual small language models on the original dataset and our translated version to compare their ability to exploit relevant reasoning steps to produce correct answers. Our results show that, in comparable settings, reasoning context is beneficial for more challenging non-binary questions, but models struggle to employ relevant Bangla reasoning steps effectively. We conclude by exploring how reasoning steps contribute to models' predictions, highlighting different trends across models and languages.

Autonomous driving technology is spearheading a transformation in the global automotive industries, and its safe and reliable implementation is the core prerequisite for large-scale adoption (Ren et al., 2025). Comprehensive testing and evaluation of autonomous driving systems (ADSs) are essential to ensuring their safety, in which the identification and generation of safety-critical scenarios represent a core challenge (Yang et al., 2025). "Safety-critical scenarios" specifically refer to rare driving situations with potentially high risks (Ding et al., 2023). Conducting tests under such scenarios enables effective evaluation of the ADSs' safety performance, as well as the clarification and iterative refinement of its Operational Design Domain (ODD). However, due to the rarity of safety-critical scenarios in naturalistic driving environments (Feng et al., 2023), real-world road testing is inefficient and cost-prohibitive, making it unsuitable for large-scale testing of high-level ADSs. As a more efficient and practical solution, simulation-based testing has garnered significant industrial and scholarly attention (Sun et al., 2022). In recent years, engineers in enterprises generally extract safety-critical testing scenarios by directly replaying vehicle-collected data in simulation environments (Liu et al., 2024), while some researchers achieve accelerated sampling of safety-critical scenarios through optimization-based search within a predefined scenario parameter space (Wu et al., 2024, 2026). However, the background vehicles (BVs) in the safety-critical testing scenarios generated by the aforementioned methods exhibit fixed behaviors and cannot dynamically respond to the actions of the vehicle under test (VUT). As a remedy, some other studies have introduced reinforcement learning to train adversarial BV driver models, thereby constructing naturalistic adversarial driving environments (NADE) (Feng et al., 2021) or evolving scenarios (Ma et al., 2024; Wu et al., 2025).

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors into simplified reasoning with latent embeddings, rendering the reasoning chain opaque and essentially intractable. We therefore adopt an explicit decomposition perspective and introduce ReVSeg, which executes reasoning as sequential decisions in the native interface of pretrained vision language models (VLMs). Rather than folding all reasoning into a single-step prediction, ReVSeg executes three explicit operations -- semantics interpretation, temporal evidence selection, and spatial grounding -- aligning pretrained capabilities. We further employ reinforcement learning to optimize the multi-step reasoning chain, enabling the model to self-refine its decision quality from outcome-driven signals. Experimental results demonstrate that ReVSeg attains state-of-the-art performances on standard video object segmentation benchmarks and yields interpretable reasoning trajectories. Project page is available at https://clementine24.github.io/ReVSeg/ .

Stock price prediction is challenging due to market volatility and its sensitivity to real-time events. While large language models (LLMs) offer new avenues for text-based forecasting, their application in finance is hindered by noisy news data and the lack of explicit answers in text. General-purpose memory architectures struggle to identify the key drivers of price movements. To address this, we propose StockMem, an event-reflection dual-layer memory framework. It structures news into events and mines them along two dimensions: horizontal consolidation integrates daily events, while longitudinal tracking captures event evolution to extract incremental information reflecting market expectation discrepancies. This builds a temporal event knowledge base. By analyzing event-price dynamics, the framework further forms a reflection knowledge base of causal experiences. For prediction, it retrieves analogous historical scenarios and reasons with current events, incremental data, and past experiences. Experiments show StockMem outperforms existing memory architectures and provides superior, explainable reasoning by tracing the information chain affecting prices, enhancing decision transparency in financial forecasting.

Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in either limits the performance of VLMs. Prior efforts to enhance reasoning often depend on high-quality chain-of-thought (CoT) data, obtained via labor-intensive human annotations, costly proprietary models, or self-training methods that overlook perception. To address these limitations, we propose a simple yet effective self-training framework called See-Think-Learn (STL). At its core, STL introduces a structured reasoning template that encourages the model to see before thinking, first extracting visual attributes in textual form, then using them to guide reasoning. The framework jointly improves perception and reasoning by having the model generate and learn from its own structured rationales in a self-training loop. Furthermore, we augment the training data with negative rationales, i.e. explanations that justify why certain answer choices are incorrect, to enhance the model's ability to distinguish between correct and misleading responses. This fosters more discriminative and robust learning. Experiments across diverse domains show that STL consistently outperforms baselines trained directly only on answers or self-generated reasoning, while qualitative analysis confirms the high quality of its rationales. STL thus provides a cost-effective solution to enhance multimodal reasoning ability of VLMs.

Recent advances in general-purpose AI systems with attention-based transformers offer a potential window into how the neocortex and cerebellum, despite their relatively uniform circuit architectures, give rise to diverse functions and, ultimately, to human intelligence. This Perspective provides a cross-domain comparison between the brain and AI that goes beyond the traditional focus on visual processing, adopting the emerging perspecive of world-model-based computation. Here, we identify shared computational mechanisms in the attention-based neocortex and the non-attentional cerebellum: both predict future world events from past inputs and construct internal world models through prediction-error learning. These predictive world models are repurposed for seemingly distinct functions -- understanding in sensory processing and generation in motor processing -- enabling the brain to achieve multi-domain capabilities and human-like adaptive intelligence. Notably, attention-based AI has independently converged on a similar learning paradigm and world-model-based computation. We conclude that these shared mechanisms in both biological and artificial systems constitute a core computational foundation for realizing diverse functions including high-level intelligence, despite their relatively uniform circuit structures. Our theoretical insights bridge neuroscience and AI, advancing our understanding of the computational essence of intelligence.

World models have gained significant attention as a promising approach for autonomous driving. By emulating human-like perception and decision-making processes, these models can predict and adapt to dynamic environments. Existing methods typically map high-dimensional observations into compact latent spaces and learn optimal policies within these latent representations. However, prior work usually jointly learns ego-vehicle dynamics and environmental transition dynamics from the image input, leading to inefficiencies and a lack of robustness to variations in vehicle dynamics. To address these issues, we propose the Vehicle Dynamics embedded Dreamer (VDD) method, which decouples the modeling of ego-vehicle dynamics from environmental transition dynamics. This separation allows the world model to generalize effectively across vehicles with diverse parameters. Additionally, we introduce two strategies to further enhance the robustness of the learned policy: Policy Adjustment during Deployment (PAD) and Policy Augmentation during Training (PAT). Comprehensive experiments in simulated environments demonstrate that the proposed model significantly improves both driving performance and robustness to variations in vehicle dynamics, outperforming existing approaches.

How do language models use contextual information to answer health questions? How are their responses impacted by conflicting contexts? We assess the ability of language models to reason over long, conflicting biomedical contexts using HealthContradict, an expert-verified dataset comprising 920 unique instances, each consisting of a health-related question, a factual answer supported by scientific evidence, and two documents presenting contradictory stances. We consider several prompt settings, including correct, incorrect or contradictory context, and measure their impact on model outputs. Compared to existing medical question-answering evaluation benchmarks, HealthContradict provides greater distinctions of language models' contextual reasoning capabilities. Our experiments show that the strength of fine-tuned biomedical language models lies not only in their parametric knowledge from pretraining, but also in their ability to exploit correct context while resisting incorrect context.

Reinforcement Learning (RL) following Supervised Fine-Tuning (SFT) has become the standard paradigm for post-training Large Language Models (LLMs). However, the mechanism by which RL contributes to reasoning capabilities-- whether it incentivizes the synthesis of new skills or merely amplifies existing behaviors--remains a subject of intense debate. In this work, we investigate this question through the lens of Complementary Reasoning, a complex task that requires integrating internal parametric knowledge with external contextual information. Using a controlled synthetic dataset of human biographies, we strictly decouple this ability into two atomic skills: Parametric Reasoning (relying on internal knowledge encoded in model parameters) and Contextual Reasoning (depending on novel information provided in the context window). To rigorously assess capability boundaries, we evaluate generalization across three distinct levels of difficulty: I.I.D., Composition, and Zero-shot settings. We find that while SFT is sufficient for in-distribution performance, it struggles with out-of-distribution generalization, particularly in Zero-shot settings where relational combinations are novel. Crucially, we identify the SFT Generalization Paradox: Models supervised solely on the composite task achieve near-perfect in-distribution accuracy (90%) but collapse on out-of-distribution generalization (18%), indicating their reliance on rote memorization of path shortcuts. In contrast, we find that RL acts as a reasoning synthesizer rather than a probability amplifier. However, we uncover a strict atomic prerequisite: RL can only synthesize these complex strategies if the base model has first mastered the independent atomic skills (Parametric and Contextual) via SFT. These findings challenge the view of RL as a mere amplifier, suggesting that given sufficient atomic foundations, RL can actively synthesize complex reasoning strategies from learned primitives without explicit supervision on such complex strategies. This indicates that decoupled atomic training followed by RL offers a scalable path to generalization for complex reasoning tasks. Code and data will be at https://github.com/sitaocheng/from The rapid evolution of Large Language Models (LLMs) has been fundamentally driven by advanced post-training strategies, specifically an initial Supervised Fine-Tuning (SFT) stage followed by a Reinforcement Learning (RL) stage (Achiam et al., 2023; Team et al., 2024; Guo et al., 2025). While SFT is effective at establishing behavioral norms and imparting foundational knowledge, it fundamentally relies on maximum likelihood estimation, which tends to favor the memorization of the training distribution.