English
Related papers

Related papers: Safety is Non-Compositional: A Formal Framework fo…

200 papers

Developing safe autonomous driving systems is a major scientific and technical challenge. Existing AI-based end-to-end solutions do not offer the necessary safety guarantees, while traditional systems engineering approaches are defeated by…

Multiagent Systems · Computer Science 2026-02-24 Marius Bozga , Joseph Sifakis

Compositionality has traditionally been understood as a major factor in productivity of language and, more broadly, human cognition. Yet, recently, some research started to question its status, showing that artificial neural networks are…

Computation and Language · Computer Science 2022-06-13 Michal Auersperger , Pavel Pecina

As AI systems become increasingly capable, safety strategies must be evaluated not only by how much they reduce present risk, but by whether they could sustain safety once external control can no longer reliably constrain system behavior.…

Artificial Intelligence · Computer Science 2026-05-14 James M. Mazzu

AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing has improved the behavior of modern language models, but aligned behavior does not by…

Artificial Intelligence · Computer Science 2026-05-27 Yige Li , Yunhao Feng , Jun Sun

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…

Artificial Intelligence · Computer Science 2020-02-20 Henrik J. Putzer , Ernest Wozniak

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…

Artificial Intelligence · Computer Science 2026-02-17 William Waites

Customer service automation is undergoing a structural transformation. The dominant paradigm is shifting from scripted chatbots and single-agent responders toward networks of specialised AI agents that compose capabilities dynamically…

Artificial Intelligence · Computer Science 2026-03-20 Cosimo Spera

As autonomy becomes prevalent in many applications, ranging from recommendation systems to fully autonomous vehicles, there is an increased need to provide safety guarantees for such systems. The problem is difficult, as these are large,…

Artificial Intelligence · Computer Science 2018-10-22 Corina S. Pasareanu , Divya Gopinath , Huafeng Yu

Compositionality is one of the fundamental abilities of the human reasoning process, that allows to decompose a complex problem into simpler elements. Such property is crucial also for neural networks, especially when aiming for a more…

Machine Learning · Computer Science 2025-06-19 Luigi Quarantiello , Andrea Cossu , Vincenzo Lomonaco

This article presents a formal model demonstrating that genuine autonomy, the ability of a system to self-regulate and pursue objectives, fundamentally implies computational unpredictability from an external perspective. we establish…

Artificial Intelligence · Computer Science 2025-09-17 Poria Azadi

As AI regulations around the world intensify their focus on system safety, contestability has become a mandatory, yet ill-defined, safeguard. In XAI, "contestability" remains an empty promise: no formal definition exists, no algorithm…

Computers and Society · Computer Science 2025-06-03 Catarina Moreira , Anna Palatkina , Dacia Braca , Dylan M. Walsh , Peter J. Leihn , Fang Chen , Nina C. Hubig

The design of a complex system warrants a compositional methodology, i.e., composing simple components to obtain a larger system that exhibits their collective behavior in a meaningful way. We propose an automaton-based paradigm for…

Logic in Computer Science · Computer Science 2023-02-03 Tobias Kappé , Farhad Arbab , Carolyn Talcott

Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital intensity, physical bottlenecks, organizational inertia, and specialized supply chains. By…

Artificial Intelligence · Computer Science 2026-05-05 Wesley Shu , Peng Wei

Systems are typically made from simple components regardless of their complexity. While the function of each part is easily understood, higher order functions are emergent properties and are notoriously difficult to explain. In networked…

Artificial Intelligence · Computer Science 2018-01-18 Jory Schossau , Larissa Albantakis , Arend Hintze

As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety properties of individual models will compose into safe multi-agent behavior. This position paper…

Artificial Intelligence · Computer Science 2026-05-05 Tanav Singh Bajaj , Nikhil Singh , Karan Anand , Eishkaran Singh

As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…

Artificial Intelligence · Computer Science 2025-08-29 Donglin Wang , Weiyun Liang , Chunyuan Chen , Jing Xu , Yulong Fu

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…

Artificial Intelligence · Computer Science 2026-05-12 Royce Moon , Lav R. Varshney

The disastrous vulnerabilities in smart contracts sharply remind us of our ignorance: we do not know how to write code that is secure in composition with malicious code. Information flow control has long been proposed as a way to achieve…

Cryptography and Security · Computer Science 2023-07-21 Ethan Cecchetti , Siqiu Yao , Haobin Ni , Andrew C. Myers

Ttraditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems which are acting in largely…

Artificial Intelligence · Computer Science 2022-05-13 Harald Rueß , Simon Burton

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

‹ Prev 1 2 3 10 Next ›