English
Related papers

Related papers: Bounded Autonomy for Enterprise AI: Typed Action C…

200 papers

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Machine Learning · Computer Science 2025-07-04 Mary Phuong , Roland S. Zimmermann , Ziyue Wang , David Lindner , Victoria Krakovna , Sarah Cogan , Allan Dafoe , Lewis Ho , Rohin Shah

We introduce an architecture for studying the behavior of large language model (LLM) agents in the absence of externally imposed tasks. Our continuous reason and act framework, using persistent memory and self-feedback, enables sustained…

Artificial Intelligence · Computer Science 2025-09-26 Stefan Szeider

As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This…

Artificial Intelligence · Computer Science 2025-07-04 Joseph Boland

Agentic AI systems, which leverage multiple autonomous agents and large language models (LLMs), are increasingly used to address complex, multi-step tasks. The safety, security, and functionality of these systems are critical, especially in…

Artificial Intelligence · Computer Science 2026-04-16 Edoardo Allegrini , Ananth Shreekumar , Z. Berkay Celik

Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on…

Artificial Intelligence · Computer Science 2026-05-26 Jia Huang , Joey Tianyi Zhou

An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors…

Computation and Language · Computer Science 2024-06-04 Yotam Wolf , Noam Wies , Oshri Avnery , Yoav Levine , Amnon Shashua

Large Language Models (LLMs) exhibit nonlinear relationships between performance, cost, and token usage. This paper presents a quantitative study on structured prompting using BRAID (Bounded Reasoning for Au tonomous Inference and…

Computation and Language · Computer Science 2025-12-19 Armağan Amcalar , Eyup Cinar

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions,…

Cryptography and Security · Computer Science 2026-01-01 Jingyu Zhang

Business processes underpin a large number of enterprise operations including processing loan applications, managing invoices, and insurance claims. There is a large opportunity for infusing AI to reduce cost or provide better customer…

Artificial Intelligence · Computer Science 2020-01-22 Steve T. K. Jan , Vatche Ishakian , Vinod Muthusamy

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

Recent human-computer interaction (HCI) research has revealed a widespread misalignment between how developers design workplace artificial intelligence (AI) systems, and what workers actually need from them. Yet, little research has…

Human-Computer Interaction · Computer Science 2026-05-21 Julia De Miguel Velázquez , Sanja Šćepanović , Andrés Gvirtz , Daniele Quercia

The integration of vision-language-action (VLA) models into embodied AI (EAI) robots is rapidly advancing their ability to perform complex, long-horizon tasks in humancentric environments. However, EAI systems introduce critical security…

Artificial Intelligence · Computer Science 2025-09-04 Yiyang Huang , Zixuan Wang , Zishen Wan , Yapeng Tian , Haobo Xu , Yinhe Han , Yiming Gan

Large Language Model (LLM)-based coding agents show promise in automating software development tasks, yet they frequently fail in ways that are difficult for developers to understand and debug. While general-purpose LLMs like GPT can…

Software Engineering · Computer Science 2026-03-09 Arun Joshi

Embodied artificial intelligence emphasizes the role of an agent's body in generating human-like behaviors. The recent efforts on EmbodiedAI pay a lot of attention to building up machine learning models to possess perceiving, planning, and…

Artificial Intelligence · Computer Science 2024-10-15 Chen Gao , Baining Zhao , Weichen Zhang , Jinzhu Mao , Jun Zhang , Zhiheng Zheng , Fanhang Man , Jianjie Fang , Zile Zhou , Jinqiang Cui , Xinlei Chen , Yong Li

Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical security tension:…

Cryptography and Security · Computer Science 2026-04-29 Ignacio Peyrano

Recent research advances in Artificial Intelligence (AI) have yielded promising results for automated software vulnerability management. AI-based models are reported to greatly outperform traditional static analysis tools, indicating a…

Cryptography and Security · Computer Science 2024-05-07 Shengye Wan , Joshua Saxe , Craig Gomes , Sahana Chennabasappa , Avilash Rath , Kun Sun , Xinda Wang

Robotic systems lack a principled abstraction for organizing intelligence, capabilities, and execution in a unified manner. Existing approaches either couple skills within monolithic architectures or decompose functionality into loosely…

Robotics · Computer Science 2026-05-26 Xue Qin , Simin Luan , John See , Cong Yang , Zhijun Li

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound…

Cryptography and Security · Computer Science 2026-03-13 Ching-Yu Kao , Xinfeng Li , Shenyu Dai , Tianze Qiu , Pengcheng Zhou , Eric Hanchen Jiang , Philip Sperl

In this paper, we present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization implementations, operating collaboratively with users or autonomously. Existing…

Artificial Intelligence · Computer Science 2026-01-30 Yang Song , Anoushka Vyas , Zirui Wei , Sina Khoshfetrat Pakazad , Henrik Ohlsson , Graham Neubig