arXiv subjects

William L. Anderson

Publications and source records attributed to William L. Anderson.

5 recordsLinked to original sources

arXiv2026

Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models

Many efforts to ensure frontier AI models are safe rely on monitoring their chain-of-thought (CoT) reasoning. If models become able to perform sufficiently complex reasoning internally, without explicit thinking tokens, this would undermine such oversight. We measure how well frontier models reason without CoT across a suite of over 30,000 questions spanning 43 benchmarks in domains including math, coding, puzzles, causality, theory-of-mind, and strategic reasoning. To compare models against humans, we estimate the $50\%$-task-completion time horizon (TH): the human time required for tasks a model completes with $50\%$ success rate. We complement this with a $50\%$ reasoning token horizon: the minimum number of o3-mini reasoning tokens needed for tasks a model solves with $50\%$ success rate. We find that the no-CoT $50\%$ TH of frontier models has been doubling roughly every year over the past six years, with GPT-5.5's TH reaching over 3 minutes and reasoning token horizon exceeding 1,500 tokens. Our median estimates predict that frontier no-CoT THs could exceed 7 minutes by 2028, and 25 minutes by 2030, though these projections carry substantial uncertainty. We recommend frontier developers track this explicitly.

cs.AI↗

arXiv2026

What Should Frontier AI Developers Disclose About Internal Deployments?

Frontier AI developers are increasingly deploying highly capable models internally to automate AI R&D, but these deployments currently face limited external oversight. It is essential, therefore, that developers provide evidence that internally deployed models are safe. While recent work has highlighted the risks of internal deployments and proposed broad approaches to transparency and governance, there remains little guidance on the specific information developers should disclose about them. We address this gap by identifying key information that companies should disclose about internally deployed models across four categories: capabilities, usage, safety mitigations, and governance. For each category, we analyse the key benefits and limitations of disclosure and consider how disclosure-related risks can be mitigated. Our framework could be used by developers to inform both public transparency documents, such as model system cards, and private periodic reports required under emerging frontier AI regulation.

cs.CY↗

arXiv2026

Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents

AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential for AI's task generalization but enable new threats like secret collusion and coordinated swarm attacks. Network effects can rapidly spread privacy breaches, disinformation, jailbreaks, and data poisoning, while multi-agent dispersion and stealth optimization help adversaries evade oversight - creating novel persistent threats at a systemic level. Despite their critical importance, these security challenges remain understudied, with research fragmented across disparate fields including AI security, multi-agent learning, complex systems, cybersecurity, game theory, distributed systems, and technical AI governance. We introduce multi-agent security, a new field dedicated to securing networks of AI agents against threats that emerge or amplify through their interactions - whether direct or indirect via shared environments - with each other, humans, and institutions, and characterise fundamental security-utility and security-security trade-offs across both distributed and decentralised settings. Our preliminary work (1) taxonomizes the threat landscape arising from interacting AI agents, (2) offers applications to multi-agent security for work across diffuse subfields, and (3) proposes a unified research agenda addressing open challenges in designing secure agent systems and interaction environments. By identifying these gaps, we aim to guide research in this critical area to unlock the socioeconomic potential of large-scale agent deployment, foster public trust, and mitigate national security risks in critical infrastructure and defense contexts.

cs.CR↗

arXiv2026

Architecture Matters for Multi-Agent Security

Multi-agent systems (MAS), composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that do not arise in single-agent settings. Even if individual agents exhibit robust security, architectural decisions governing their coordination can create attack surfaces that have not been systematically characterized. In this work, we present an empirical study of how MAS design decisions shape the tradeoff between task performance and attack resistance. Across three agentic environments (browser, desktop, and code) and 13 architectural configurations, we use stagewise evaluations that distinguish planning refusal, execution-stage interception, partial harmful execution, and successful attack completion to study three key design choices: (i) agent roles, which determine how authority and responsibility are allocated; (ii) communication topology, which shapes how and when agents interact; and (iii) memory, which determines the context and state visibility accessible to each agent. We find that multi-agent architectures are more vulnerable than standalone agents in the majority of configurations, with attack success rates varying by up to 3.8x at comparable or higher benign accuracy, and that no single design is universally safer. These results motivate the development of further evaluations that move beyond the security properties of a single agent.

cs.MA↗

arXiv2010

Software Must Move! A Description of the Software Assembly Line

This paper describes a set of tools for automating and controlling the development and maintenance of software systems. The mental model is a software assembly line. Program design and construction take place at individual programmer workstations. Integration of individual software components takes place at subsequent stations on the assembly line. Software is moved automatically along the assembly line toward final packaging. Software under construction or maintenance is divided into packages. Each package of software is composed of a recipe and ingredients. Some new terms are introduced to describe the ingredients. The recipe specifies how ingredients are transformed into products. The benefits of the Software Assembly Line for development, maintenance, and management of large-scale computer systems are explained.

cs.SE↗