The recent progress of large language model agents has opened new possibilities for automating tasks through graphical user interfaces (GUIs), especially in mobile environments where intelligent interaction can greatly enhance usability. However, practical deployment of such agents remains constrained by several key challenges. Existing training data is often noisy and lack semantic diversity, which hinders the learning of precise grounding and planning. Models trained purely by imitation tend to overfit to seen interface patterns and fail to generalize in unfamiliar scenarios. Moreover, most prior work focuses on English interfaces while overlooks the growing diversity of non-English applications such as those in the Chinese mobile ecosystem. In this work, we present AgentCPM-GUI, an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction. Our training pipeline includes grounding-aware pre-training to enhance perception, supervised fine-tuning on high-quality Chinese and English trajectories to imitate human-like actions, and reinforcement fine-tuning with GRPO to improve reasoning capability. We also introduce a compact action space that reduces output length and supports low-latency execution on mobile devices. AgentCPM-GUI achieves state-of-the-art performance on five public benchmarks and a new Chinese GUI benchmark called CAGUI, reaching $96.9\%$ Type-Match and $91.3\%$ Exact-Match. To facilitate reproducibility and further research, we publicly release all code, model checkpoint, and evaluation data.

Recent works on large language models (LLMs) have successfully demonstrated the emergence of reasoning capabilities via reinforcement learning (RL). Although recent efforts leverage group relative policy optimization (GRPO) for MLLMs post-training, they constantly explore one specific aspect, such as grounding tasks, math problems, or chart analysis. There are no works that can leverage multi-source MLLM tasks for stable reinforcement learning. In this work, we present a unified perspective to solve this problem. We present Mixed-R1, a unified yet straightforward framework that contains a mixed reward function design (Mixed-Reward) and a mixed post-training dataset (Mixed-45K). We first design a data engine to select high-quality examples to build the Mixed-45K post-training dataset. Then, we present a Mixed-Reward design, which contains various reward functions for various MLLM tasks. In particular, it has four different reward functions: matching reward for binary answer or multiple-choice problems, chart reward for chart-aware datasets, IoU reward for grounding problems, and open-ended reward for long-form text responses such as caption datasets. To handle the various long-form text content, we propose a new open-ended reward named Bidirectional Max-Average Similarity (BMAS) by leveraging tokenizer embedding matching between the generated response and the ground truth. Extensive experiments show the effectiveness of our proposed method on various MLLMs, including Qwen2.5-VL and Intern-VL on various sizes. Our dataset and model are available at https://github.com/xushilin1/mixed-r1.

Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal understanding, yet their capabilities for scientific reasoning remain inadequately assessed. Current multimodal benchmarks predominantly evaluate generic image comprehension or text-driven reasoning, lacking authentic scientific contexts that require domain-specific knowledge integration with visual evidence analysis. To fill this gap, we present CSVQA, a diagnostic multimodal benchmark specifically designed for evaluating scientific reasoning through domain-grounded visual question answering. Our benchmark features 1,378 carefully constructed question-answer pairs spanning diverse STEM disciplines, each demanding domain knowledge, integration of visual evidence, and higher-order reasoning. Compared to prior multimodal benchmarks, CSVQA places greater emphasis on real-world scientific content and complex reasoning. We additionally propose a rigorous evaluation protocol to systematically assess whether model predictions are substantiated by valid intermediate reasoning steps based on curated explanations. Our comprehensive evaluation of 15 VLMs on this benchmark reveals notable performance disparities, as even the top-ranked proprietary model attains only 49.6% accuracy. This empirical evidence underscores the pressing need for advancing scientific reasoning capabilities in VLMs. Our CSVQA is released at https://huggingface.co/datasets/Skywork/CSVQA

Fine-grained robot manipulation, such as lifting and rotating a bottle to display the label on the cap, requires robust reasoning about object parts and their relationships with intended tasks. Despite recent advances in training general-purpose robot manipulation policies guided by language instructions, there is a notable lack of large-scale datasets for fine-grained manipulation tasks with part-level instructions and diverse 3D object instances annotated with part-level labels. In this work, we introduce PartInstruct, the first large-scale benchmark for training and evaluating fine-grained robot manipulation models using part-level instructions. PartInstruct comprises 513 object instances across 14 categories, each annotated with part-level information, and 1302 fine-grained manipulation tasks organized into 16 task classes. Our training set consists of over 10,000 expert demonstrations synthesized in a 3D simulator, where each demonstration is paired with a high-level task instruction, a chain of base part-based skill instructions, and ground-truth 3D information about the object and its parts. Additionally, we designed a comprehensive test suite to evaluate the generalizability of learned policies across new states, objects, and tasks. We evaluated several state-of-the-art robot manipulation approaches, including end-to-end vision-language policy learning and bi-level planning models for robot manipulation on our benchmark. The experimental results reveal that current models struggle to robustly ground part concepts and predict actions in 3D space, and face challenges when manipulating object parts in long-horizon tasks.

Role-based access control (RBAC) and hierarchical structures are foundational to how information flows and decisions are made within virtually all organizations. As the potential of Large Language Models (LLMs) to serve as unified knowledge repositories and intelligent assistants in enterprise settings becomes increasingly apparent, a critical, yet under explored, challenge emerges: \textit{can these models reliably understand and operate within the complex, often nuanced, constraints imposed by organizational hierarchies and associated permissions?} Evaluating this crucial capability is inherently difficult due to the proprietary and sensitive nature of real-world corporate data and access control policies. We introduce a synthetic yet representative \textbf{OrgAccess} benchmark consisting of 40 distinct types of permissions commonly relevant across different organizational roles and levels. We further create three types of permissions: 40,000 easy (1 permission), 10,000 medium (3-permissions tuple), and 20,000 hard (5-permissions tuple) to test LLMs' ability to accurately assess these permissions and generate responses that strictly adhere to the specified hierarchical rules, particularly in scenarios involving users with overlapping or conflicting permissions. Our findings reveal that even state-of-the-art LLMs struggle significantly to maintain compliance with role-based structures, even with explicit instructions, with their performance degrades further when navigating interactions involving two or more conflicting permissions. Specifically, even \textbf{GPT-4.1 only achieves an F1-Score of 0.27 on our hardest benchmark}. This demonstrates a critical limitation in LLMs' complex rule following and compositional reasoning capabilities beyond standard factual or STEM-based benchmarks, opening up a new paradigm for evaluating their fitness for practical, structured environments.

Collaborative dialogue offers rich insights into students' learning and critical thinking, which is essential for personalizing pedagogical agent interactions in STEM+C settings. While large language models (LLMs) facilitate dynamic pedagogical interactions, hallucinations undermine confidence, trust, and instructional value. Retrieval-augmented generation (RAG) grounds LLM outputs in curated knowledge but requires a clear semantic link between user input and a knowledge base, which is often weak in student dialogue. We propose log-contextualized RAG (LC-RAG), which enhances RAG retrieval by using environment logs to contextualize collaborative discourse. Our findings show that LC-RAG improves retrieval over a discourse-only baseline and allows our collaborative peer agent, Copa, to deliver relevant, personalized guidance that supports students' critical thinking and epistemic decision-making in a collaborative computational modeling environment, C2STEM.

LLMs enable an exciting new class of data processing applications over large collections of unstructured documents. Several new programming frameworks have enabled developers to build these applications by composing them out of semantic operators: a declarative set of AI-powered data transformations with natural language specifications. These include LLM-powered maps, filters, joins, etc. used for document processing tasks such as information extraction, summarization, and more. While systems of semantic operators have achieved strong performance on benchmarks, they can be difficult to optimize. An optimizer for this setting must determine how to physically implement each semantic operator in a way that optimizes the system globally. Existing optimizers are limited in the number of optimizations they can apply, and most (if not all) cannot optimize system quality, cost, or latency subject to constraint(s) on the other dimensions. In this paper we present Abacus, an extensible, cost-based optimizer which searches for the best implementation of a semantic operator system given a (possibly constrained) optimization objective. Abacus estimates operator performance by leveraging a minimal set of validation examples and, if available, prior beliefs about operator performance. We evaluate Abacus on document processing workloads in the biomedical and legal domains (BioDEX; CUAD) and multi-modal question answering (MMQA). We demonstrate that systems optimized by Abacus achieve 18.7%-39.2% better quality and up to 23.6x lower cost and 4.2x lower latency than the next best system.

Prompt injection remains a major security risk for large language models. However, the efficacy of existing guardrail models in context-aware settings remains underexplored, as they often rely on static attack benchmarks. Additionally, they have over-defense tendencies. We introduce CAPTURE, a novel context-aware benchmark assessing both attack detection and over-defense tendencies with minimal in-domain examples. Our experiments reveal that current prompt injection guardrail models suffer from high false negatives in adversarial cases and excessive false positives in benign scenarios, highlighting critical limitations. To demonstrate our framework's utility, we train CaptureGuard on our generated data. This new model drastically reduces both false negative and false positive rates on our context-aware datasets while also generalizing effectively to external benchmarks, establishing a path toward more robust and practical prompt injection defenses.

This demo paper reports on a new workflow \textit{GhostWriter} that combines the use of Large Language Models and Knowledge Graphs (semantic artifacts) to support navigation through collections. Situated in the research area of Retrieval Augmented Generation, this specific workflow represents the creation of local and adaptable chatbots. Based on the tool-suite \textit{EverythingData} at the backend, \textit{GhostWriter} provides an interface that enables querying and ``chatting'' with a collection. Applied iteratively, the workflow supports the information needs of researchers when interacting with a collection of papers, whether it be to gain an overview, to learn more about a specific concept and its context, and helps the researcher ultimately to refine their research question in a controlled way. We demonstrate the workflow for a collection of articles from the \textit{method data analysis} journal published by GESIS -- Leibniz-Institute for the Social Sciences. We also point to further application areas.

Large language models (LLMs) have been widely deployed as autonomous agents capable of following user instructions and making decisions in real-world applications. Previous studies have made notable progress in benchmarking the instruction following capabilities of LLMs in general domains, with a primary focus on their inherent commonsense knowledge. Recently, LLMs have been increasingly deployed as domain-oriented agents, which rely on domain-oriented guidelines that may conflict with their commonsense knowledge. These guidelines exhibit two key characteristics: they consist of a wide range of domain-oriented rules and are subject to frequent updates. Despite these challenges, the absence of comprehensive benchmarks for evaluating the domain-oriented guideline following capabilities of LLMs presents a significant obstacle to their effective assessment and further development. In this paper, we introduce GuideBench, a comprehensive benchmark designed to evaluate guideline following performance of LLMs. GuideBench evaluates LLMs on three critical aspects: (i) adherence to diverse rules, (ii) robustness to rule updates, and (iii) alignment with human preferences. Experimental results on a range of LLMs indicate substantial opportunities for improving their ability to follow domain-oriented guidelines.