Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules.The challenge lies in ensuring that the agent consistently adheres to these rules and policies, appropriately refusing any request that would violate them, while still maintaining a helpful and natural interaction.This calls for the development of tailored design and evaluation methodologies to ensure agent resilience against malicious user behavior.We propose a novel threat model that focuses on adversarial users aiming to exploit policy-adherent agents for personal benefit.To address this, we present CRAFT, a multi-agent red-teaming system that leverages policy-aware persuasive strategies to undermine a policy-adherent agent in a customerservice scenario, outperforming conventional jailbreak methods such as DAN prompts, emotional manipulation, and coercive.Building upon the existing τ -bench benchmark, we introduce τ -break, a complementary benchmark designed to rigorously assess the agent's robustness against manipulative user behavior.Finally, we evaluate several straightforward yet effective defense strategies.While these measures provide some protection, they fall short, highlighting the need for stronger, researchdriven safeguards to protect policy-adherent agents from adversarial attacks. 1 .

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially synthesize new labeled data for supervised learning. We mainly focus on cases with scarce labeled data. Our method, referred to as language-model-based data augmentation (LAMBADA), involves fine-tuning a state-of-the-art language generator to a specific task through an initial training phase on the existing (usually small) labeled data. Using the fine-tuned model and given a class label, new sentences for the class are generated. Our process then filters these new sentences by using a classifier trained on the original data. In a series of experiments, we show that LAMBADA improves classifiers' performance on a variety of datasets. Moreover, LAMBADA significantly improves upon the state-of-the-art techniques for data augmentation, specifically those applicable to text classification tasks with little data.

Real-time performance is necessary in applications involving on-line handwriting recognition. However, conventional approaches usually wait until the entire curve is traced out before starting the analysis, inevitably causing delays in the recognition process. In regards to the Arabic script, the postponed analysis may be attributed to the cursive and unconstrained nature of the Arabic writing system, in both printed and handwritten forms. Nevertheless, this paper proposes a real-time recognition-based segmentation technique of on-line Arabic script. It demonstrate the feasibility of carrying out the most time consuming tasks, required for the segmentation process, during the course of writing. The system has been designed and tested using the ADAB Database, and promising results were obtained.