Understanding high-resolution images remains a significant challenge for multimodal large language models (MLLMs). Recent study address this issue by dividing the image into smaller crops and computing the semantic similarity between each crop and a query using a pretrained retrieval-augmented generation (RAG) model. The most relevant crops are then selected to localize the target object and suppress irrelevant information. However, such crop-based processing can fragment complete objects across multiple crops, thereby disrupting the computation of semantic similarity. In our experiments, we find that image crops of objects with different sizes are better handled at different resolutions. Based on this observation, we propose Multi-resolution Retrieval-Detection (MRD), a training-free framework for high-resolution image understanding. To address the issue of semantic similarity bias caused by objects being split across different image crops, we propose a multi-resolution semantic fusion method, which integrates semantic similarity maps obtained at different resolutions to produce more accurate semantic information and preserve the integrity of target objects. Furthermore, to achieve direct localization of target objects at a global scale, we introduce an open-vocalbulary object detection (OVD) model that identifies object regions using a sliding-window approach.Experiments on high-resolution image understanding benchmarks using different MLLMs demonstrate the effectiveness of our approach.

This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We evaluate 7 leading commercial and open-source MLLMs across 18 real-world CAPTCHA task types, measuring single-shot accuracy, success under limited retries, end-to-end latency, and per-solve cost. We further analyze the impact of task-specific prompt engineering and few-shot demonstrations on solver effectiveness. We reveal that MLLMs can reliably solve recognition-oriented and low-interaction CAPTCHA tasks at human-like cost and latency, whereas tasks requiring fine-grained localization, multi-step spatial reasoning, or cross-frame consistency remain significantly harder for current models. By examining the reasoning traces of such MLLMs, we investigate the underlying mechanisms of why models succeed/fail on specific CAPTCHA puzzles and use these insights to derive defense-oriented guidelines for selecting and strengthening CAPTCHA tasks. We conclude by discussing implications for platform operators deploying CAPTCHA as part of their abuse-mitigation pipeline.Code Availability (https://anonymous.4open.science/r/Captcha-465E/).

Artificial Intelligence (AI) chatbots powered by a large language model (LLM) are entering young children's learning and play, yet little is known about how young children construe these agents or how such construals relate to engagement. We examined anthropomorphism of a social AI chatbot during collaborative storytelling and asked how children's attributions related to their behavior and prefrontal activation. Children at ages 5-6 (N = 23) completed three storytelling sessions: interacting with (1) an AI chatbot only, (2) a parent only, and (3) the AI and a parent together. After the sessions, children completed an interview assessing anthropomorphism toward both the AI chatbot and the parent. Behavioral engagement was indexed by the conversational turn count (CTC) ratio, and concurrent fNIRS measured oxygenated hemoglobin in bilateral vmPFC and dmPFC regions. Children reported higher anthropomorphism for parents than for the AI chatbot overall, although AI ratings were relatively high for perceptive abilities and epistemic states. Anthropomorphism was not associated with CTC. In the right dmPFC, higher perceptive scores were associated with greater activation during the AI-only condition and with lower activation during the AI+Parent condition. Exploratory analyses indicated that higher dmPFC activation during the AI-only condition correlated with higher end-of-session "scared" mood ratings. Findings suggest that stronger perceptive anthropomorphism can be associated with greater brain activation related to interpreting the AI's mental states, whereas parent co-presence may help some children interpret and regulate novel AI interactions. These results may have design implications for encouraging parent-AI co-use in early childhood.

Flowcharts are common tools for communicating processes but are often shared as static images that cannot be easily edited or reused. We present Flowchart2Mermaid, a lightweight web system that converts flowchart images into editable Mermaid.js code which is a markup language for visual workflows, using a detailed system prompt and vision-language models. The interface supports mixed-initiative refinement through inline text editing, drag-and-drop node insertion, and natural-language commands interpreted by an integrated AI assistant. Unlike prior image-to-diagram tools, our approach produces a structured, version-controllable textual representation that remains synchronized with the rendered diagram. We further introduce evaluation metrics to assess structural accuracy, flow correctness, syntax validity, and completeness across multiple models.

Large language model based agents are increasingly deployed in complex, tool augmented environments. While reinforcement learning provides a principled mechanism for such agents to improve through interaction, its effectiveness critically depends on the availability of structured training tasks. In many realistic settings, however, no such tasks exist a challenge we term task scarcity, which has become a key bottleneck for scaling agentic RL. Existing approaches typically assume predefined task collections, an assumption that fails in novel environments where tool semantics and affordances are initially unknown. To address this limitation, we formalize the problem of Task Generation for Agentic RL, where an agent must learn within a given environment that lacks predefined tasks. We propose CuES, a Curiosity driven and Environment grounded Synthesis framework that autonomously generates diverse, executable, and meaningful tasks directly from the environment structure and affordances, without relying on handcrafted seeds or external corpora. CuES drives exploration through intrinsic curiosity, abstracts interaction patterns into reusable task schemas, and refines them through lightweight top down guidance and memory based quality control. Across three representative environments, AppWorld, BFCL, and WebShop, CuES produces task distributions that match or surpass manually curated datasets in both diversity and executability, yielding substantial downstream policy improvements. These results demonstrate that curiosity driven, environment grounded task generation provides a scalable foundation for agents that not only learn how to act, but also learn what to learn. The code is available at https://github.com/modelscope/AgentEvolver/tree/main/research/CuES.

Electronic health records (EHRs) support powerful clinical prediction models, but existing methods typically provide coarse, post hoc explanations that offer limited value for patient-level decision making. We introduce a knowledge graph (KG)-guided chain-of-thought (CoT) framework that generates clinically grounded and temporally consistent reasoning for visit-level disease prediction in MIMIC-III. ICD-9 codes are mapped to PrimeKG, from which disease-relevant nodes and multi-hop reasoning paths are extracted and used as scaffolds for CoT generation; only explanations whose conclusions match observed outcomes are retained. Lightweight LLaMA-3.1-Instruct-8B and Gemma-7B models are then fine-tuned on this supervision corpus. Across ten PrimeKG-mapped diseases and limited training cohorts (400 and 1000 cases), KG-guided models outperform strong classical baselines, achieving AUROC values of 0.66 to 0.70 and macro-AUPR values of 0.40 to 0.47. The models also transfer zero-shot to the CRADLE cohort, improving accuracy from approximately 0.40 to 0.51 up to 0.72 to 0.77. A blinded clinician evaluation shows consistent preference for KG-guided CoT explanations in clarity, relevance, and clinical correctness.

Vision - Language Models (VLMs) exhibit significant performance plateaus in specialized domains like precision agriculture, primarily due to "Reasoning - Driven Hallucination" where linguistic priors override visual perception. A key bottleneck is the "Modalit y Gap": visual embeddings fail to reliably activate the fine - grained expert knowledge already encoded in model parameters. We propose "Look, Recite, Then Answer," a parameter - efficient framework that enhances VLMs via self - generated knowledge hints while keeping backbone models frozen. The framework decouples inference into three stages: (1) Look generates objective visual des criptions and candidate sets; (2) Recite employs a lightweight 1.7B router to transform visual cues into targeted queries that trigger candidate - specific parametric knowledge; (3) Answer performs parallel evidence alignment between descriptions and recited knowledge to select the most consistent label. On AgroBench, our method achieves state - of - the - art results, improving Weed Identification accuracy by 23. 52 % over Qwen2 - VL - 72B and surpassing GPT - 4o without external search overhead. Vision - Language Models (VLMs) have advanced by synergizing visual representations with linguistic reasoning. Empirical analyses fro m AgroBench reveal a critical failure mode: "Reasoning - Driven Hallucination." (Shinoda et al., 2025) .

Recent advances in large language models (LLMs) have shown strong reasoning capabilities through large-scale pretraining and post-training reinforcement learning, demonstrated by DeepSeek-R1. However, current post-training methods, such as Grouped Relative Policy Optimization (GRPO), mainly reward correctness, which is not aligned with the multi-dimensional objectives required in high-stakes fields such as medicine, where reasoning must also be faithful and comprehensive. We introduce Clinical-Objective Relative Policy Optimization (CRPO), a scalable, multi-objective, verifiable reinforcement learning method designed to align LLM post-training with clinical reasoning principles. CRPO integrates rule-based and verifiable reward signals that jointly optimize accuracy, faithfulness, and comprehensiveness without relying on human annotation. To demonstrate its effectiveness, we train Clinical-R1-3B, a 3B-parameter model for clinical reasoning. The experiments on three benchmarks demonstrate that our CRPO substantially improves reasoning on truthfulness and completeness over standard GRPO while maintaining comfortable accuracy enhancements. This framework provides a scalable pathway to align LLM reasoning with clinical objectives, enabling safer and more collaborative AI systems for healthcare while also highlighting the potential of multi-objective, verifiable RL methods in post-training scaling of LLMs for medical domains.

As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an empirically demonstrated risk across language models, AI agents, and emerging frontier systems. This project provides a comprehensive and up-to-date overview of the AI deception field, covering its core concepts, methodologies, genesis, and potential mitigations. First, we identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception. We then review existing empirical studies and associated risks, highlighting deception as a sociotechnical safety challenge. We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment. Deception emergence reveals the mechanisms underlying AI deception: systems with sufficient capability and incentive potential inevitably engage in deceptive behaviors when triggered by external conditions. Deception treatment, in turn, focuses on detecting and addressing such behaviors. On deception emergence, we analyze incentive foundations across three hierarchical levels and identify three essential capability preconditions required for deception. We further examine contextual triggers, including supervision gaps, distributional shifts, and environmental pressures. On deception treatment, we conclude detection methods covering benchmarks and evaluation protocols in static and interactive settings. Building on the three core factors of deception emergence, we outline potential mitigation strategies and propose auditing approaches that integrate technical, community, and governance efforts to address sociotechnical challenges and future AI risks. To support ongoing work in this area, we release a living resource at www.deceptionsurvey.com.

Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays an important role in determining the quality of their outputs. Mainstream denoising strategies include Standard Diffusion and BlockDiffusion. Standard Diffusion performs global denoising without restricting the update range, often finalizing incomplete context and causing premature end-of-sequence predictions. BlockDiffusion updates fixed-size blocks in a preset order, but its rigid structure can break apart coherent semantic units and disrupt reasoning. We present WavefrontDiffusion, a dynamic decoding approach that expands a wavefront of active tokens outward from finalized positions. This adaptive process follows the natural flow of semantic structure while keeping computational cost equal to block-based methods. Across four benchmarks in reasoning and code generation, WavefrontDiffusion achieves state-of-the-art performance while producing outputs with higher semantic fidelity, showing the value of adaptive scheduling for more coherent and efficient generation. Recent advances in large language models (LLMs) have achieved remarkable progress in complex reasoning and structured generation tasks such as mathematical problem solving and code synthesis (OpenAI et al., 2025; DeepSeek-AI et al., 2025). Autoregressive (AR) models remain the dominant paradigm for these tasks due to their stepwise logical consistency (Deletang et al., 2024). However, their strictly sequential nature introduces latency and limits flexibility, which can be problematic in settings that demand both accuracy and responsiveness, such as interactive assistants or real-time code generation. These limitations have motivated the exploration of alternative decoding paradigms that can balance quality, efficiency, and adaptability (Leviathan et al., 2023). Diffusion Language Models (DLMs) have recently emerged as a promising alternative by framing text generation as an iterative denoising process (Gong et al., 2025; Song et al., 2025).