Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against attacks that aim to elicit harmful actions from agents. To this end, we propose a novel taxonomy of harms for agentic systems and a novel benchmark, BAD-ACTS, for studying the security of agentic systems with respect to a wide range of harmful actions. BAD-ACTS consists of 4 implementations of agentic systems in distinct application environments, as well as a dataset of 188 high-quality examples of harmful actions. This enables a comprehensive study of the robustness of agentic systems across a wide range of categories of harmful behaviors, available tools, and inter-agent communication structures. Using this benchmark, we analyze the robustness of agentic systems against an attacker that controls one of the agents in the system and aims to manipulate other agents to execute a harmful target action. Our results show that the attack has a high success rate, demonstrating that even a single adversarial agent within the system can have a significant impact on the security. This attack remains effective even when agents use a simple prompting-based defense strategy. However, we additionally propose a more effective defense based on message monitoring. We believe that this benchmark provides a diverse testbed for the security research of agentic systems. The benchmark can be found at github.com/JNoether/BAD-ACTS

Large language models (LLMs) have demonstrated significant capabilities in solving mathematical problems expressed in natural language. However, multilingual and culturally-grounded mathematical reasoning in low-resource languages lags behind English due to the scarcity of socio-cultural task datasets that reflect accurate native entities such as person names, organization names, and currencies. Existing multilingual benchmarks are predominantly produced via translation and typically retain English-centric entities, owing to the high cost associated with human annotater-based localization. Moreover, automated localization tools are limited, and hence, truly localized datasets remain scarce. To bridge this gap, we introduce a framework for LLM-driven cultural localization of math word problems that automatically constructs datasets with native names, organizations, and currencies from existing sources. We find that translated benchmarks can obscure true multilingual math ability under appropriate socio-cultural contexts. Through extensive experiments, we also show that our framework can help mitigate English-centric entity bias and improves robustness when native entities are introduced across various languages.

Modern large language models often encode sensitive, harmful, or copyrighted knowledge, raising the need for post-hoc unlearning-the ability to remove specific domains of knowledge from a model without full retraining. A major bottleneck in current unlearning pipelines is constructing effective forget sets-datasets that approximate the target domain and guide the model to forget it. In this work, we introduce a scalable, automated approach to generate high-quality forget sets using language models themselves. Our method synthesizes textbook-style data through a structured prompting pipeline, requiring only a domain name as input. Through experiments on unlearning biosecurity, cybersecurity, and Harry Potter novels, we show that our synthetic datasets consistently outperform the baseline synthetic alternatives and are comparable to the expert-curated ones. Additionally, ablation studies reveal that the multi-step generation pipeline significantly boosts data diversity, which in turn improves unlearning utility. Overall, our findings suggest that synthetic datasets offer a promising path toward practical, scalable unlearning for a wide range of emerging domains without the need for manual intervention. We release our code and dataset at https://github.com/xyzhu123/Synthetic_Textbook.

The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such content with the final goal of lightening up political deliberation to citizens. However, the specificity of the political language and the argumentative form of these debates (employing hidden communication strategies and leveraging implicit arguments) make this task very challenging, even for current general-purpose pre-trained Language Models. To address this issue, we introduce a novel pre-trained Language Model for political discourse language called RooseBERT. Pre-training a language model on a specialised domain presents different technical and linguistic challenges, requiring extensive computational resources and large-scale data. RooseBERT has been trained on large political debate and speech corpora (8K debates, each composed of several sub-debates on different topics) in English. To evaluate its performances, we fine-tuned it on four downstream tasks related to political debate analysis, i.e., stance detection, sentiment analysis, argument component detection and classification, and argument relation prediction and classification. Our results demonstrate significant improvements over general-purpose Language Models on these four tasks, highlighting how domain-specific pre-training enhances performance in political debate analysis. We release RooseBERT for the research community.

Speed bumps and potholes are the most common road anomalies, significantly affecting ride comfort and vehicle stability. Preview-based suspension control mitigates their impact by detecting such irregularities in advance and adjusting suspension parameters proactively. Accurate and real-time detection is essential, but embedded deployment is constrained by limited computational resources and the small size of targets in input images.To address these challenges, this paper proposes SBP-YOLO, an efficient detection framework for speed bumps and potholes in embedded systems. Built upon YOLOv11n, it integrates GhostConv and VoVGSCSPC modules in the backbone and neck to reduce computation while enhancing multi-scale semantic features. A P2-level branch improves small-object detection, and a lightweight and efficient detection head (LEDH) maintains accuracy with minimal overhead. A hybrid training strategy further enhances robustness under varying road and environmental conditions, combining NWD loss, BCKD knowledge distillation, and Albumentations-based augmentation. Experiments show that SBP-YOLO achieves 87.0% mAP, outperforming the YOLOv11n baseline by 5.8%. After TensorRT FP16 quantization, it runs at 139.5 FPS on Jetson AGX Xavier, yielding a 12.4% speedup over the P2-enhanced YOLOv11. These results demonstrate the framework's suitability for fast, low-latency road condition perception in embedded suspension control systems.

Knowledge editing aims to modify outdated knowledge in large language models (LLMs) efficiently while retaining their original capabilities. Mainstream benchmarks for knowledge editing are predominantly static and fail to keep in pace with the evolving real-world knowledge. In this work, we introduce CRAFT, an ever-evolving real-world benchmark for knowledge editing. It features well-designed paired edits for composite reasoning, and evaluates models on alias portability as well as temporal and common-sense locality, making it a challenging knowledge editing benchmark on which previous knowledge editing methods hardly achieve balanced performance. Towards flexible real-time editing, we propose KEDAS, a novel paradigm of knowledge editing alignment featuring diverse edit augmentation and self-adaptive post-alignment inference, which exhibits significant performance gain on CRAFT compared to previous methods. All of our code and data are available at https://anonymous.4open.science/r/CRAFT-KEDAS.

Relation Extraction (RE) is a fundamental task in Natural Language Processing, and its document-level variant poses significant challenges, due to complex interactions between entities across sentences. While supervised models have achieved strong results in fully resourced settings, their behavior with limited training data remains insufficiently studied. We introduce GLiDRE, a new compact model for document-level relation extraction, designed to work efficiently in both supervised and few-shot settings. Experiments in both low-resource supervised training and few-shot meta-learning benchmarks show that our approach outperforms existing methods in data-constrained scenarios, establishing a new state-of-the-art in few-shot document-level relation extraction. Our code will be publicly available.

Current artificial intelligence systems show near-human-level capabilities when deployed in isolation. Systems of a few collaborating intelligent agents are being engineered to perform tasks collectively. This raises the question of whether robotic matter, where many learning and intelligent agents interact, shows emergence of collective behaviour. And if so, which kind of phenomena would such systems exhibit? Here, we study a paradigmatic model for robotic matter: a stochastic many-particle system in which each particle is endowed with a deep neural network that predicts its transitions based on the particles' environments. For a one-dimensional model, we show that robotic matter exhibits complex emergent phenomena, including transitions between long-lived learning regimes, the emergence of particle species, and frustration. We also find a density-dependent phase transition with signatures of criticality. Using active matter theory, we show that this phase transition is a consequence of self-organisation mediated by emergent inter-particle interactions. Our simple model captures key features of more complex forms of robotic systems.

This study investigates the adoption of open-access, locally deployable causal large language models (LLMs) for travel mode choice prediction and introduces LiTransMC, the first fine-tuned causal LLM developed for this task. We systematically benchmark eleven open-access LLMs (1-12B parameters) across three stated and revealed preference datasets, testing 396 configurations and generating over 79,000 mode choice decisions. Beyond predictive accuracy, we evaluate models generated reasoning using BERTopic for topic modelling and a novel Explanation Strength Index, providing the first structured analysis of how LLMs articulate decision factors in alignment with behavioural theory. LiTransMC, fine-tuned using parameter efficient and loss masking strategy, achieved a weighted F1 score of 0.6845 and a Jensen-Shannon Divergence of 0.000245, surpassing both untuned local models and larger proprietary systems, including GPT-4o with advanced persona inference and embedding-based loading, while also outperforming classical mode choice methods such as discrete choice models and machine learning classifiers for the same dataset. This dual improvement, i.e., high instant-level accuracy and near-perfect distributional calibration, demonstrates the feasibility of creating specialist, locally deployable LLMs that integrate prediction and interpretability. Through combining structured behavioural prediction with natural language reasoning, this work unlocks the potential for conversational, multi-task transport models capable of supporting agent-based simulations, policy testing, and behavioural insight generation. These findings establish a pathway for transforming general purpose LLMs into specialized and explainable tools for transportation research and policy formulation, while maintaining privacy, reducing cost, and broadening access through local deployment.

The increasing volume of academic literature makes it essential for researchers to organize, compare, and contrast collections of documents. Large language models (LLMs) can support this process by generating schemas defining shared aspects along which to compare papers. However, progress on schema generation has been slow due to: (i) ambiguity in reference-based evaluations, and (ii) lack of editing/refinement methods. Our work is the first to address both issues. First, we present an approach for augmenting unannotated table corpora with \emph{synthesized intents}, and apply it to create a dataset for studying schema generation conditioned on a given information need, thus reducing ambiguity. With this dataset, we show how incorporating table intents significantly improves baseline performance in reconstructing reference schemas. We start by comprehensively benchmarking several single-shot schema generation methods, including prompted LLM workflows and fine-tuned models, showing that smaller, open-weight models can be fine-tuned to be competitive with state-of-the-art prompted LLMs. Next, we propose several LLM-based schema refinement techniques and show that these can further improve schemas generated by these methods.