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 .

The research on online learning under stationary and ergodic processes has been mainly focused on achieving asymptotic guarantees. Although all the methods pursue the same asymptotic goal, their performance varies when handling finite sample datasets and depends heavily on which predefined density estimation method is chosen. In this paper, therefore, we propose a novel algorithm that simultaneously satisfies a short-term goal, to perform as good as the best choice in hindsight of a data-adaptive kernel, learned using a deep neural network, and a long-term goal, to achieve the same theoretical asymptotic guarantee. We present theoretical proofs for our algorithms and demonstrate the validity of our method on the online portfolio selection problem.

In this paper we focus on the problem of online portfolio selection with transaction costs. We tackle this problem using a novel approach for combining the predictions of long-term experts with those of short-term experts so as to effectively reduce transaction costs. We prove that the new strategy maintains bounded regret relative to the performance of the best possible combination (switching times) of the long-and short-term experts. We empirically validate our approach on several standard benchmark datasets. These studies indicate that the proposed approach achieves state-of-the-art performance.

User generated reviews is a highly informative source of information, that has recently gained lots of attention in the recommender systems community. In this work we propose a generative latent variable model that explains both observed ratings and textual reviews. This latent variable model allows to combine any traditional collaborative filtering method, together with any deep learning architecture for text processing. Experimental results on four benchmark datasets demonstrate its superiority comparing to all baseline recommender systems. Furthermore, a running time analysis shows that this approach is in order of magnitude faster that relevant baselines. Moreover, underlying our solution there is a general framework that may be further explored.

Online portfolio selection research has so far focused mainly on minimizing regret defined in terms of wealth growth. Practical financial decision making, however, is deeply concerned with both wealth and risk. We consider online learning of portfolios of stocks whose prices are governed by arbitrary (unknown) stationary and ergodic processes, where the goal is to maximize wealth while keeping the conditional value at risk (CVaR) below a desired threshold. We characterize the asymptomatically optimal risk-adjusted performance and present an investment strategy whose portfolios are guaranteed to achieve the asymptotic optimal solution while fulfilling the desired risk constraint. We also numerically demonstrate and validate the viability of our method on standard datasets.

Online-learning research has mainly been focusing on minimizing one objective function. In many real-world applications, however, several objective functions have to be considered simultaneously. Recently, an algorithm for dealing with several objective functions in the i.i.d. case has been presented. In this paper, we extend the multi-objective framework to the case of stationary and ergodic processes, thus allowing dependencies among observations. We first identify an asymptomatic lower bound for any prediction strategy and then present an algorithm whose predictions achieve the optimal solution while fulfilling any continuous and convex constraining criterion.