Dawn Song

Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi et al. · stanford

Cutting-edge agentic AI systems are built on foundation models that can be adapted to plan, reason, and interact with external tools to perform increasingly complex and specialized tasks. As these systems grow in capability and scope, adaptation becomes a central mechanism for improving performance, reliability, and generalization. In this paper, we unify the rapidly expanding research landscape into a systematic framework that spans both agent adaptations and tool adaptations. We further decompose these into tool-execution-signaled and agent-output-signaled forms of agent adaptation, as well as agent-agnostic and agent-supervised forms of tool adaptation. We demonstrate that this framework helps clarify the design space of adaptation strategies in agentic AI, makes their trade-offs explicit, and provides practical guidance for selecting or switching among strategies during system design. We then review the representative approaches in each category, analyze their strengths and limitations, and highlight key open challenges and future opportunities. Overall, this paper aims to offer a conceptual foundation and practical roadmap for researchers and practitioners seeking to build more capable, efficient, and reliable agentic AI systems.

Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao et al. · berkeley

The rapid development of large reasoning models (LRMs), such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large language models~(LLMs). However, their enhanced capabilities, combined with the open-source access of models like DeepSeek-R1, raise serious safety concerns, particularly regarding their potential for misuse. In this work, we present a comprehensive safety assessment of these reasoning models, leveraging established safety benchmarks to evaluate their compliance with safety regulations. Furthermore, we investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications. Through our multi-faceted analysis, we uncover four key findings: (1) There is a significant safety gap between the open-source reasoning models and the o3-mini model, on both safety benchmark and attack, suggesting more safety effort on open LRMs is needed. (2) The stronger the model's reasoning ability, the greater the potential harm it may cause when answering unsafe questions. (3) Safety thinking emerges in the reasoning process of LRMs, but fails frequently against adversarial attacks. (4) The thinking process in R1 models poses greater safety concerns than their final answers. Our study provides insights into the security implications of reasoning models and highlights the need for further advancements in R1 models' safety to close the gap.

Will Cai, Tianneng Shi, Xuandong Zhao et al. · berkeley

Commercial Large Language Model (LLM) APIs create a fundamental trust problem: users pay for specific models but have no guarantee that providers deliver them faithfully. Providers may covertly substitute cheaper alternatives (e.g., quantized versions, smaller models) to reduce costs while maintaining advertised pricing. We formalize this model substitution problem and systematically evaluate detection methods under realistic adversarial conditions. Our empirical analysis reveals that software-only methods are fundamentally unreliable: statistical tests on text outputs are query-intensive and fail against subtle substitutions, while methods using log probabilities are defeated by inherent inference nondeterminism in production environments. We argue that this verification gap can be more effectively closed with hardware-level security. We propose and evaluate the use of Trusted Execution Environments (TEEs) as one practical and robust solution. Our findings demonstrate that TEEs can provide provable cryptographic guarantees of model integrity with only a modest performance overhead, offering a clear and actionable path to ensure users get what they pay for. Code is available at https://github.com/sunblaze-ucb/llm-api-audit

Yueheng Zhang, Xiaoyuan Liu, Yiyou Sun et al.

We evaluate questions generated by large language models (LLMs) from context, comparing them to human-authored questions across six dimensions: question type, question length, context coverage, answerability, uncommonness, and required answer length. Our study spans two open-source and two proprietary state-of-the-art models. Results reveal that LLM-generated questions tend to demand longer descriptive answers and exhibit more evenly distributed context focus, in contrast to the positional bias often seen in QA tasks. These findings provide insights into the distinctive characteristics of LLM-generated questions and inform future work on question quality and downstream applications.

Tianneng Shi, Kaijie Zhu, Zhun Wang et al. · berkeley

Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specified task rather than the intended task provided by the user. In this paper, we present PromptArmor, a simple yet effective defense against prompt injection attacks. Specifically, PromptArmor prompts an off-the-shelf LLM to detect and remove potential injected prompts from the input before the agent processes it. Our results show that PromptArmor can accurately identify and remove injected prompts. For example, using GPT-4o, GPT-4.1, or o4-mini, PromptArmor achieves both a false positive rate and a false negative rate below 1% on the AgentDojo benchmark. Moreover, after removing injected prompts with PromptArmor, the attack success rate drops to below 1%. We also demonstrate PromptArmor's effectiveness against adaptive attacks and explore different strategies for prompting an LLM. We recommend that PromptArmor be adopted as a standard baseline for evaluating new defenses against prompt injection attacks.

Yoshua Bengio, Tegan Maharaj, Luke Ong et al. · cmu, mila

Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy, reliable, and secure. Building a trusted ecosystem is therefore essential -- it helps people embrace AI with confidence and gives maximal space for innovation while avoiding backlash. The "2025 Singapore Conference on AI (SCAI): International Scientific Exchange on AI Safety" aimed to support research in this space by bringing together AI scientists across geographies to identify and synthesise research priorities in AI safety. This resulting report builds on the International AI Safety Report chaired by Yoshua Bengio and backed by 33 governments. By adopting a defence-in-depth model, this report organises AI safety research domains into three types: challenges with creating trustworthy AI systems (Development), challenges with evaluating their risks (Assessment), and challenges with monitoring and intervening after deployment (Control).

Dan Hendrycks, Dawn Song, Christian Szegedy et al.

The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quantifiable framework to address this, defining AGI as matching the cognitive versatility and proficiency of a well-educated adult. To operationalize this, we ground our methodology in Cattell-Horn-Carroll theory, the most empirically validated model of human cognition. The framework dissects general intelligence into ten core cognitive domains-including reasoning, memory, and perception-and adapts established human psychometric batteries to evaluate AI systems. Application of this framework reveals a highly "jagged" cognitive profile in contemporary models. While proficient in knowledge-intensive domains, current AI systems have critical deficits in foundational cognitive machinery, particularly long-term memory storage. The resulting AGI scores (e.g., GPT-4 at 27%, GPT-5 at 57%) concretely quantify both rapid progress and the substantial gap remaining before AGI.

Sayash Kapoor, Benedikt Stroebl, Peter Kirgis et al. · microsoft-research, princeton

AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic Agent Leaderboard (HAL) to address these challenges. We make three main contributions. First, we provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of VMs, reducing evaluation time from weeks to hours while eliminating common implementation bugs. Second, we conduct three-dimensional analysis spanning models, scaffolds, and benchmarks. We validate the harness by conducting 21,730 agent rollouts across 9 models and 9 benchmarks in coding, web navigation, science, and customer service with a total cost of about $40,000. Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs. Third, we use LLM-aided log inspection to uncover previously unreported behaviors, such as searching for the benchmark on HuggingFace instead of solving a task, or misusing credit cards in flight booking tasks. We share all agent logs, comprising 2.5B tokens of language model calls, to incentivize further research into agent behavior. By standardizing how the field evaluates agents and addressing common pitfalls in agent evaluation, we hope to shift the focus from agents that ace benchmarks to agents that work reliably in the real world.

Ziheng Cheng, Yixiao Huang, Hui Xu et al. · berkeley

Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to prevent harmful outputs, they often lead to overly cautious behavior -- rejecting even benign prompts -- a phenomenon known as $\textit{over-refusal}$ that reduces the practical utility of T2I models. Despite over-refusal having been observed in practice, there is no large-scale benchmark that systematically evaluates this phenomenon for T2I models. In this paper, we present an automatic workflow to construct synthetic evaluation data, resulting in OVERT ($\textbf{OVE}$r-$\textbf{R}$efusal evaluation on $\textbf{T}$ext-to-image models), the first large-scale benchmark for assessing over-refusal behaviors in T2I models. OVERT includes 4,600 seemingly harmful but benign prompts across nine safety-related categories, along with 1,785 genuinely harmful prompts (OVERT-unsafe) to evaluate the safety-utility trade-off. Using OVERT, we evaluate several leading T2I models and find that over-refusal is a widespread issue across various categories (Figure 1), underscoring the need for further research to enhance the safety alignment of T2I models without compromising their functionality. As a preliminary attempt to reduce over-refusal, we explore prompt rewriting; however, we find it often compromises faithfulness to the meaning of the original prompts. Finally, we demonstrate the flexibility of our generation framework in accommodating diverse safety requirements by generating customized evaluation data adapting to user-defined policies.

Yi Zeng, Kevin Klyman, Andy Zhou et al.

We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a significant step towards establishing a unified language for generative AI safety evaluation. We identify 314 unique risk categories organized into a four-tiered taxonomy. At the highest level, this taxonomy encompasses System & Operational Risks, Content Safety Risks, Societal Risks, and Legal & Rights Risks. The taxonomy establishes connections between various descriptions and approaches to risk, highlighting the overlaps and discrepancies between public and private sector conceptions of risk. By providing this unified framework, we aim to advance AI safety through information sharing across sectors and the promotion of best practices in risk mitigation for generative AI models and systems.