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 .

We present models which complete missing text given transliterations of ancient Mesopotamian documents, originally written on cuneiform clay tablets (2500 BCE -100 CE).Due to the tablets' deterioration, scholars often rely on contextual cues to manually fill in missing parts in the text in a subjective and time-consuming process.We identify that this challenge can be formulated as a masked language modelling task, used mostly as a pretraining objective for contextualized language models.Following, we develop several architectures focusing on the Akkadian language, the lingua franca of the time.We find that despite data scarcity (1M tokens) we can achieve state of the art performance on missing tokens prediction (89% hit@5) using a greedy decoding scheme and pretraining on data from other languages and different time periods.Finally, we conduct human evaluations showing the applicability of our models in assisting experts to transcribe texts in extinct languages.