Chart understanding plays a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. However, existing datasets often focus on oversimplified and homogeneous charts with template-based questions, leading to an overly optimistic measure of progress. We demonstrate that although open-source models can appear to outperform strong proprietary models on these benchmarks, a simple stress test with slightly different charts or questions deteriorates performance by up to 34.5%. In this work, we propose CharXiv, a comprehensive evaluation suite involving 2,323 natural, challenging, and diverse charts from scientific papers. CharXiv includes two types of questions: 1) descriptive questions about examining basic chart elements and 2) reasoning questions that require synthesizing information across complex visual elements in the chart. To ensure quality, all charts and questions are handpicked, curated, and verified by human experts. Our results reveal a substantial, previously underestimated gap between the reasoning skills of the strongest proprietary model (i.e., GPT-4o), which achieves 47.1% accuracy, and the strongest open-source model (i.e., InternVL Chat V1.5), which achieves 29.2%. All models lag far behind human performance of 80.5%, underscoring weaknesses in the chart understanding capabilities of existing MLLMs. We hope that CharXiv facilitates future research on MLLM chart understanding by providing a more realistic and faithful measure of progress.

Solving mathematical problems requires advanced reasoning abilities and presents notable challenges for large language models. Previous works usually synthesize data from proprietary models to augment existing datasets, followed by instruction tuning to achieve top-tier results. However, our analysis of these datasets reveals severe biases towards easy queries, with frequent failures to generate any correct response for the most challenging queries.Hypothesizing that difficult queries are crucial to learning complex reasoning, we propose (), a method that allocates difficult queries more trials during the synthesis phase, enabling more extensive training on difficult samples.Utilizing, we have created new datasets for mathematical problem-solving that focus more on difficult queries and are substantially smaller than previous ones. Remarkably, our synthesis process solely relies on a 7B-sized open-weight model, without reliance on the commonly used proprietary GPT-4.We fine-tune various base models on our datasets ranging from 7B to 70B in size, resulting in a series of strong models called .In comprehensive in-domain and out-of-domain evaluation on 6 mathematical benchmarks, outperforms vanilla rejection tuning significantly, being superior or comparable to previous arts, despite using much smaller datasets and no proprietary models.

Discharge Summaries are documents written by medical professionals that detail a patient's visit to a care facility. They contain a wealth of information crucial for patient care, and automating their generation could significantly reduce the effort required from healthcare professionals, minimize errors, and ensure that critical patient information is easily accessible and actionable. In this work, we explore the use of five Large Language Models on this task, from open-source models (Mistral, Llama 2) to proprietary systems (GPT-3, GPT-4, Gemini 1.5 Pro), leveraging MIMIC-III summaries and notes. We evaluate them using exact-match, soft-overlap, and reference-free metrics. Our results show that proprietary models, particularly Gemini with one-shot prompting, outperformed others, producing summaries with the highest similarity to the gold-standard ones. Open-source models, while promising, especially Mistral after fine-tuning, lagged in performance, often struggling with hallucinations and repeated information. Human evaluation by a clinical expert confirmed the practical utility of the summaries generated by proprietary models. Despite the challenges, such as hallucinations and missing information, the findings suggest that LLMs, especially proprietary models, are promising candidates for automatic discharge summary generation as long as data privacy is ensured.

While Large Language Models (LLMs) are increasingly used for synthesizing textual PLC programming languages like Structured Text (ST) code, other IEC 61131-3 standard graphical languages like Sequential Function Charts (SFCs) remain underexplored. Generating SFCs is challenging due to graphical nature and ST actions embedded within, which are not directly compatible with standard generation techniques, often leading to non-executable code that is incompatible with industrial tool-chains In this work, we introduce LLM4SFC, the first framework to receive natural-language descriptions of industrial workflows and provide executable SFCs. LLM4SFC is based on three components: (i) A reduced structured representation that captures essential topology and in-line ST and reduced textual verbosity; (ii) Fine-tuning and few-shot retrieval-augmented generation (RAG) for alignment with SFC programming conventions; and (iii) A structured generation approach that prunes illegal tokens in real-time to ensure compliance with the textual format of SFCs. We evaluate LLM4SFC on a dataset of real-world SFCs from automated manufacturing projects, using both open-source and proprietary LLMs. The results show that LLM4SFC reliably generates syntactically valid SFC programs effectively bridging graphical and textual PLC languages, achieving a generation generation success of 75% - 94%, paving the way for automated industrial programming.

As Large Language Models (LLMs) transition from code completion tools to autonomous system architects, their impact on long-term software maintainability remains unquantified. While existing research benchmarks functional correctness (pass@k), this study presents the first empirical framework to measure "Architectural Erosion" and the accumulation of Technical Debt in AI-synthesized microservices. We conducted a comparative pilot study of three state-of-the-art models (GPT-5.1, Claude 4.5 Sonnet, and Llama 3 8B) by prompting them to implement a standardized Book Lending Microservice under strict Hexagonal Architecture constraints. Utilizing Abstract Syntax Tree (AST) parsing, we find that while proprietary models achieve high architectural conformance (0% violation rate for GPT-5.1), open-weights models exhibit critical divergence. Specifically, Llama 3 demonstrated an 80% Architectural Violation Rate, frequently bypassing interface adapters to create illegal circular dependencies between Domain and Infrastructure layers. Furthermore, we identified a phenomenon of "Implementation Laziness," where open-weights models generated 60% fewer Logical Lines of Code (LLOC) than their proprietary counterparts, effectively omitting complex business logic to satisfy token constraints. These findings suggest that without automated architectural linting, utilizing smaller open-weights models for system scaffolding accelerates the accumulation of structural technical debt.

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model generate incoherent or confidently incorrect outputs. Practical applications include embedding such adversarial images into websites to prevent MLLM-powered AI Agents from operating reliably. The proposed attack maximizes next-token entropy using a small ensemble of open-source MLLMs. In the white-box setting, we show that a single adversarial image can disrupt all models in the ensemble, both in the full-image and Adversarial CAPTCHA settings. Despite relying on a basic adversarial technique (PGD), the attack generates perturbations that transfer to both unseen open-source (e.g., Qwen3-VL) and proprietary (e.g., GPT-5.1)

Large Language Models (LLMs) often exhibit inconsistent behavior when answering paraphrased questions, suggesting a reliance on surface-level patterns rather than true semantic understanding. To address this limitation, we introduce RoParQ, a benchmark specifically constructed to evaluate cross-paraphrase consistency in closed-book multiple-choice QA. This benchmark is derived from standard datasets by generating paraphrases via proprietary models and selectively retaining examples that elicit inconsistent confidence from a judge model. We further propose XParaCon, a novel evaluation metric that quantifies a model's robustness by measuring the standard deviation of accuracies across question variants. Additionally, we implement a reasoning-based, paraphrase-aware Supervised Fine-Tuning (SFT) strategy designed to align models toward semantic invariance. Our experiments demonstrate that this targeted alignment significantly enhances robustness. Notably, fine-tuned lightweight models achieved consistency levels comparable to much larger pre-trained models. These results highlight the efficacy of our approach in mitigating superficial memorization and fostering more robust, reliable LLMs.

Large language models must satisfy hard orthographic constraints during controlled text generation, yet systematic cross-architecture evaluation remains limited. We evaluate 28 configurations spanning three model families (Qwen3, Claude Haiku-4.5, GPT-5-mini) on 58 word puzzles requiring character-level constraint satisfaction. Architectural differences produce substantially larger performance gaps (2.0-2.2x, F1=0.761 vs. 0.343) than parameter scaling within families (83% gain from eightfold scaling), suggesting that constraint satisfaction may require specialized architectural features or training objectives beyond standard language model scaling. Thinking budget sensitivity proves heterogeneous: high-capacity models show strong returns (+0.102 to +0.136 F1), while mid-sized variants saturate or degrade. These patterns are inconsistent with uniform compute benefits. Using difficulty ratings from 10,000 human solvers per puzzle, we establish modest but consistent calibration (r=0.24-0.38) across all families, yet identify systematic failures on common words with unusual orthography ("data", "poop", "loll": 86-95% human success, 89-96% model miss rate). These failures reveal over-reliance on distributional plausibility that penalizes orthographically atypical but constraint-valid patterns, suggesting architectural innovations may be required beyond simply scaling parameters or computational budgets.

Large Language Models (LLMs) have emerged as transformative tools for natural language understanding and user intent resolution, enabling tasks such as translation, summarization, and, increasingly, the orchestration of complex workflows. This development signifies a paradigm shift from conventional, GUI-driven user interfaces toward intuitive, language-first interaction paradigms. Rather than manually navigating applications, users can articulate their objectives in natural language, enabling LLMs to orchestrate actions across multiple applications in a dynamic and contextual manner. However, extant implementations frequently rely on cloud-based proprietary models, which introduce limitations in terms of privacy, autonomy, and scalability. For language-first interaction to become a truly robust and trusted interface paradigm, local deployment is not merely a convenience; it is an imperative. This limitation underscores the importance of evaluating the feasibility of locally deployable, open-source, and open-access LLMs as foundational components for future intent-based operating systems. In this study, we examine the capabilities of several open-source and open-access models in facilitating user intention resolution through machine assistance. A comparative analysis is conducted against OpenAI's proprietary GPT-4-based systems to assess performance in generating workflows for various user intentions. The present study offers empirical insights into the practical viability, performance trade-offs, and potential of open LLMs as autonomous, locally operable components in next-generation operating systems. The results of this study inform the broader discussion on the decentralization and democratization of AI infrastructure and point toward a future where user-device interaction becomes more seamless, adaptive, and privacy-conscious through locally embedded intelligence.