中文
相关论文

相关论文: Do Biological Structural Guarantees Earn Their Com…

200 篇论文

This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges…

人工智能 · 计算机科学 2025-12-11 Sławomir Nowaczyk

We introduce a mathematically rigorous framework for an artificial intelligence system composed of probabilistic agents evolving through structured competition and belief revision. The architecture, grounded in Bayesian inference, measure…

人工智能 · 计算机科学 2025-06-25 Craig Steven Wright

AI agents dynamically acquire tools, orchestrate sub-agents, and transact across organizational boundaries, yet no existing security layer verifies what an agent can do, whether it executed what it claims, or what happened in a multi-agent…

密码学与安全 · 计算机科学 2026-03-23 Ziling Zhou

AI governance programmes increasingly rely on natural language prompts to constrain and direct AI agent behaviour. These prompts function as executable specifications: they define the agent's mandate, scope, and quality criteria. Despite…

软件工程 · 计算机科学 2026-04-24 Christo Zietsman

With recent and rapid advancements in artificial intelligence (AI), understanding the foundation of purposeful behaviour in autonomous agents is crucial for developing safe and efficient systems. While artificial neural networks have…

人工智能 · 计算机科学 2025-08-12 Aswin Paul , Moein Khajehnejad , Forough Habibollahi , Brett J. Kagan , Adeel Razi

This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI governance frameworks enacted between 2019 and early 2026 require reviewable evidence of…

机器学习 · 计算机科学 2026-05-15 Pratinav Seth , Vinay Kumar Sankarapu

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider…

AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…

人工智能 · 计算机科学 2026-01-06 Bin Xu

The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…

人工智能 · 计算机科学 2025-09-30 Roham Koohestani

AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing…

软件工程 · 计算机科学 2026-04-20 Yining Hong , Yining She , Eunsuk Kang , Christopher S. Timperley , Christian Kästner

This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level…

人工智能 · 计算机科学 2026-05-12 Harsh Raj , Niranjan Orkat , Suvrorup Mukherjee , Aritra Guha , Cheryl Flynn , Subhabrata Majumdar

We analyze the challenges of benchmarking scientific (multi)-agentic systems, including the difficulty of distinguishing reasoning from retrieval, the risks of data/model contamination, the lack of reliable ground truth for novel research…

计算机与社会 · 计算机科学 2026-04-07 Marcin Abram

Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…

人工智能 · 计算机科学 2026-05-12 Royce Moon , Lav R. Varshney

Developing safe, aligned agentic AI systems requires comprehensive empirical testing, yet many existing benchmarks neglect crucial themes aligned with biology and economics, both time-tested fundamental sciences describing our needs and…

多智能体系统 · 计算机科学 2025-12-01 Roland Pihlakas

A formal but intuitive framework is introduced to bridge the gap between data obtained from empirical studies and that generated by agent-based models. This is based on three key tenets. Firstly, a simulation can be given multiple formal…

多智能体系统 · 计算机科学 2013-02-21 Chih-Chun Chen

Autonomous systems with cognitive features are on their way into the market. Within complex environments, they promise to implement complex and goal oriented behavior even in a safety related context. This behavior is based on a certain…

人工智能 · 计算机科学 2020-02-20 Henrik J. Putzer , Ernest Wozniak

This paper introduces BioAgent Bench, a benchmark dataset and an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The benchmark contains curated end-to-end tasks (e.g.,…

人工智能 · 计算机科学 2026-05-08 Dionizije Fa , Marko Culjak , Bruno Pandza , Mateo Cupic

Current AI governance frameworks, including regulatory benchmarks for accuracy, latency, and energy efficiency, are built for static, centrally trained artificial neural networks on von Neumann hardware. NeuroAI systems, embodied in…

新兴技术 · 计算机科学 2026-02-06 Afifah Kashif , Abdul Muhsin Hameed , Asim Iqbal

Engineered image-based biomarkers offer a clinically interpretable alternative to black-box AI in computational pathology, yet their discovery remains largely intuition-driven, guided by fragmented literature rather than rigorous biological…

‹ 上一页 1 2 3 10 下一页 ›