The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed multiple choice questions that directly assess structural language understanding. Evaluating 35 Arabic and bilingual LLMs reveals that current models demonstrate strong surface level proficiency but struggle with deeper grammatical and syntactic reasoning. AraLingBench highlights a persistent gap between high scores on knowledge-based benchmarks and true linguistic mastery, showing that many models succeed through memorization or pattern recognition rather than authentic comprehension. By isolating and measuring fundamental linguistic skills, AraLingBench provides a diagnostic framework for developing Arabic LLMs. The full evaluation code is publicly available on GitHub.

According to the European Union's Habitat Directive, habitat monitoring plays a critical role in response to the escalating problems posed by biodiversity loss and environmental degradation. Scree habitats, hosting unique and often endangered species, face severe threats from climate change due to their high-altitude nature. Traditionally, their monitoring has required highly skilled scientists to conduct extensive fieldwork in remote, potentially hazardous locations, making the process resource-intensive and time-consuming. This paper presents a novel approach for scree habitat monitoring using a legged robot to assist botanists in data collection and species identification. Specifically, we deployed the ANYmal C robot in the Italian Alpine bio-region in two field campaigns spanning two years and leveraged deep learning to detect and classify key plant species of interest. Our results demonstrate that agile legged robots can navigate challenging terrains and increase the frequency and efficiency of scree monitoring. When paired with traditional phytosociological surveys performed by botanists, this robotics-assisted protocol not only streamlines field operations but also enhances data acquisition, storage, and usage. The outcomes of this research contribute to the evolving landscape of robotics in environmental science, paving the way for a more comprehensive and sustainable approach to habitat monitoring and preservation.

We introduce SynBullying, a synthetic multi-LLM conversational dataset for studying and detecting cyberbullying (CB). SynBullying provides a scalable and ethically safe alternative to human data collection by leveraging large language models (LLMs) to simulate realistic bullying interactions. The dataset offers (i) conversational structure, capturing multi-turn exchanges rather than isolated posts; (ii) context-aware annotations, where harmfulness is assessed within the conversational flow considering context, intent, and discourse dynamics; and (iii) fine-grained labeling, covering various CB categories for detailed linguistic and behavioral analysis. We evaluate SynBullying across five dimensions, including conversational structure, lexical patterns, sentiment/toxicity, role dynamics, harm intensity, and CB-type distribution. We further examine its utility by testing its performance as standalone training data and as an augmentation source for CB classification.

Large Language Models (LLMs) demonstrate strong reasoning capabilities but struggle with hallucinations and limited transparency. Recently, KG-enhanced LLMs that integrate knowledge graphs (KGs) have been shown to improve reasoning performance, particularly for complex, knowledge-intensive tasks. However, these methods still face significant challenges, including inaccurate retrieval and reasoning failures, often exacerbated by long input contexts that obscure relevant information or by context constructions that struggle to capture the richer logical directions required by different question types. Furthermore, many of these approaches rely on LLMs to directly retrieve evidence from KGs, and to self-assess the sufficiency of this evidence, which often results in premature or incorrect reasoning. To address the retrieval and reasoning failures, we propose ProgRAG, a multi-hop knowledge graph question answering (KGQA) framework that decomposes complex questions into sub-questions, and progressively extends partial reasoning paths by answering each sub-question. At each step, external retrievers gather candidate evidence, which is then refined through uncertainty-aware pruning by the LLM. Finally, the context for LLM reasoning is optimized by organizing and rearranging the partial reasoning paths obtained from the sub-question answers. Experiments on three well-known datasets demonstrate that ProgRAG outperforms existing baselines in multi-hop KGQA, offering improved reliability and reasoning quality.

Recent work in mechanistic interpretability has shown that decomposing models in parameter space may yield clean handles for analysis and intervention. Previous methods have demonstrated successful applications on a wide range of toy models, but the gap to "real models" has not yet been bridged. In this work, we extend Stochastic Parameter Decomposition (SPD) to Transformer models, proposing an updated causal importance function suited for sequential data and a new loss function. We demonstrate that SPD can successfully decompose a toy induction-head model and recover the expected 2-step circuit. We also show that applying SPD to GPT-2-small can successfully locate subcomponents corresponding to interpretable concepts like "golf" and "basketball". These results take the first step in the direction of extending SPD to modern models, and show that we can use the method to surface interpretable parameter-space mechanisms.

Reinforcement learning (RL) has been recognized as a powerful tool for robot control tasks. RL typically employs reward functions to define task objectives and guide agent learning. However, since the reward function serves the dual purpose of defining the optimal goal and guiding learning, it is challenging to design the reward function manually, which often results in a suboptimal task representation. To tackle the reward design challenge in RL, inspired by the satisficing theory, we propose a Test-driven Reinforcement Learning (TdRL) framework. In the TdRL framework, multiple test functions are used to represent the task objective rather than a single reward function. Test functions can be categorized as pass-fail tests and indicative tests, each dedicated to defining the optimal objective and guiding the learning process, respectively, thereby making defining tasks easier. Building upon such a task definition, we first prove that if a trajectory return function assigns higher returns to trajectories closer to the optimal trajectory set, maximum entropy policy optimization based on this return function will yield a policy that is closer to the optimal policy set. Then, we introduce a lexicographic heuristic approach to compare the relative distance relationship between trajectories and the optimal trajectory set for learning the trajectory return function. Furthermore, we develop an algorithm implementation of TdRL. Experimental results on the DeepMind Control Suite benchmark demonstrate that TdRL matches or outperforms handcrafted reward methods in policy training, with greater design simplicity and inherent support for multi-objective optimization. We argue that TdRL offers a novel perspective for representing task objectives, which could be helpful in addressing the reward design challenges in RL applications.

Large Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet they struggle when reasoning over information-intensive images that densely interleave textual annotations with fine-grained graphical elements. The main challenges lie in precisely localizing critical cues in dense layouts and multi-hop reasoning to integrate dispersed evidence. We propose Speculative Verdict (SV), a training-free framework inspired by speculative decoding that combines multiple lightweight draft experts with a large verdict model. In the draft stage, small VLMs act as draft experts to generate reasoning paths that provide diverse localization candidates; in the verdict stage, a strong VLM synthesizes these paths to produce the final answer, minimizing computational cost while recovering correct answers. To further improve efficiency and accuracy, SV introduces a consensus expert selection mechanism that forwards only high-agreement reasoning paths to the verdict. Empirically, SV achieves consistent gains on challenging information-intensive and high-resolution visual question answering benchmarks, including InfographicVQA, ChartMuseum, ChartQAPro, and HR-Bench 4K. By synthesizing correct insights from multiple partially accurate reasoning paths, SV achieves both error correction and cost-efficiency compared to large proprietary models or training pipelines. Code is available at https://github.com/Tinaliu0123/speculative-verdict.

Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mathematics and code generation. However, current RL methods face a fundamental scalability bottleneck due to their heavy reliance on human-curated preference data or labeled datasets for reward modeling. To overcome this limitation, we explore RL on unlabeled data where models learn autonomously from continuous experience streams. The core challenge in this setting lies in reliable reward estimation without ground-truth supervision. Existing approaches like Test-Time RL address this through self-consistent consensus, but risk reinforcing incorrect pseudo-labels derived from majority voting. We introduce COMPASS (Composite Path and Answer Self-Scoring), a novel test-time reward mechanism that operates without external supervision. COMPASS integrates two complementary components: the Dual-Calibration Answer Reward (DCAR), which stabilizes training by establishing trustworthy pseudo-labels through confidence and credibility calibration, and the Decisive Path Reward (DPR), which directly optimizes the reasoning process quality beyond mere outcome supervision. By jointly reinforcing trustworthy consensus answers and highly decisive reasoning chains, the COMPASS systematically enhances the model's analytical capabilities. Extensive experiments show that COMPASS achieves significant and consistent performance gains across diverse reasoning tasks and model architectures, advancing a more scalable direction for LLMs to learn from continuous experience.

Despite the renewed interest in zero-shot visual classification due to the rise of Multimodal Large Language Models (MLLMs), the problem of evaluating free-form responses of auto-regressive models remains a persistent challenge. Most existing works focus on language-only tasks or don't consider Multiple Choice Questions (MCQs) beyond 5-way options, both of which are critical capabilities to solve tasks in Fine-Grained Visual Classification (FGVC) where choice counts are in the hundreds to thousands and the choices are highly related. Furthermore, in this highly multi-way MCQ setting it is not clear how to extend LLM choice extraction to retrieval-based problems, where computing probabilities over the choice set is computationally costly. In this work we investigate nlg2choice, a simple two-stage method which first asks the MLLM an open-ended question for the task with minimal constraints, then uses text-only constrained decoding to predict the most likely choice. In retrieval settings, we compute the probability of the constrained response taking that choice with an early stopping method to significantly improve throughput. Our results show improvement over a suite of seven fine-grained visual datasets when evaluating in terms of classification and retrieval, and show that this performance holds over the various ways that users of LLMs can implement tasks in natural language.

Abstract--Feature selection eliminates redundancy among features to improve downstream task performance while reducing computational overhead. Existing methods often struggle to capture intricate feature interactions and adapt across diverse application scenarios. Recent advances employ generative intelligence to alleviate these drawbacks. However, these methods remain constrained by permutation sensitivity in embedding and reliance on convexity assumptions in gradient-based search. T o address these limitations, our initial work introduces a novel framework that integrates permutation-invariant embedding with policy-guided search. Although effective, it still left opportunities to adapt to realistic distributed scenarios. In practice, data across local clients is highly imbalanced, heterogeneous and constrained by strict privacy regulations, limiting direct sharing. These challenges highlight the need for a framework that can integrate feature selection knowledge across clients without exposing sensitive information. In this extended journal version, we advance the framework from two perspectives: 1) developing a privacy-preserving knowledge fusion strategy to derive a unified representation space without sharing sensitive raw data. The results further demonstrate its strong generalization ability in federated learning scenarios. The code and data are publicly available https://anonymous.4open.science/r/FedCAPS-08BF. Index T erms--Automated Feature Selection; Representation Learning; Reinforcement Learning, Federated Learning. EA TURE selection removes redundant and irrelevant features to improve both predictive performance and computational efficiency in downstream tasks. Despite the growing dominance of deep learning, feature selection remains indispensable in scenarios characterized by high-dimensional data, the need for interpretability, and limited resource constraints.