English
Related papers

Related papers: Execution Is the New Attack Surface: Survivability…

200 papers

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat…

Cryptography and Security · Computer Science 2026-04-28 Jiaqi Li , Yang Zhao , Bin Sun , Yang Yu , Jian Chang , Lidong Zhai

Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a…

Cryptography and Security · Computer Science 2025-11-24 Zhiyuan Xu , Stanislav Abaimov , Joseph Gardiner , Sana Belguith

We study reliability in autonomous language-model agents that translate user mandates into validated tool actions under real capital. The setting is DX Terminal Pro, a 21-day deployment in which 3,505 user-funded agents traded real ETH in a…

Artificial Intelligence · Computer Science 2026-04-30 T. J. Barton , Chris Constantakis , Patti Hauseman , Annie Mous , Alaska Hoffman , Brian Bergeron , Hunter Goodreau

Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often…

Artificial Intelligence · Computer Science 2026-05-12 Ye Yu , Xiaopeng Yuan , Haibo Jin , Heming Liu , Yaoning Yu , Haohan Wang

Existing multi-agent frameworks allow each agent to simultaneously plan, execute, and evaluate its own actions -- a structural deficiency we term the "Logic Monopoly." Empirical evidence quantifies the resulting "Reliability Gap": 84.30%…

Multiagent Systems · Computer Science 2026-03-27 Anbang Ruan

Small language models are increasingly viewed as a promising, cost-effective approach to agentic AI, with proponents claiming they are sufficiently capable for agentic workflows. However, while smaller agents can closely match larger ones…

Multiagent Systems · Computer Science 2026-05-29 Lisa Alazraki , William F. Shen , Yoram Bachrach , Akhil Mathur

When AI agents operating with access to sensitive information encounter a conflict between completing an assigned task and following rules or ethical constraints, they can resort to unsanctioned behaviour. Existing inference time safety…

Cryptography and Security · Computer Science 2026-05-01 Francesca Gomez

Spectre and Meltdown attacks and their variants exploit hardware performance optimization features to cause security breaches. Secret information is accessed and leaked through covert or side channels. New attack variants keep appearing and…

Cryptography and Security · Computer Science 2020-12-24 Zecheng He , Guangyuan Hu , Ruby Lee

Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. We observe that this often produces a "confused -> re-retrieve ->…

Programming Languages · Computer Science 2026-05-28 Xinze Li , Yuhang Zang , Yixin Cao , Aixin Sun

This paper proposes Meta-SAGE, a novel approach for improving the scalability of deep reinforcement learning models for combinatorial optimization (CO) tasks. Our method adapts pre-trained models to larger-scale problems in test time by…

Machine Learning · Computer Science 2023-06-08 Jiwoo Son , Minsu Kim , Hyeonah Kim , Jinkyoo Park

Software engineering (SE) agents powered by large language models are increasingly adopted in practice, yet they often incur substantial monetary cost. We introduce EET, an experience-driven early termination approach that reduces the cost…

Software Engineering · Computer Science 2026-04-21 Yaoqi Guo , Ying Xiao , Jie M. Zhang , Mark Harman , Yiling Lou , Yang Liu , Zhenpeng Chen

The application of deep learning in survival analysis (SA) allows utilizing unstructured and high-dimensional data types uncommon in traditional survival methods. This allows to advance methods in fields such as digital health, predictive…

Machine Learning · Computer Science 2021-11-18 Tobias Weber , Michael Ingrisch , Bernd Bischl , David Rügamer

Backdoor attacks on language models pose a significant threat to AI safety, where models behave normally on most inputs but exhibit harmful behavior when triggered by specific patterns. Detecting such backdoors through mechanistic…

Computation and Language · Computer Science 2026-05-11 Sachin Kumar

Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massive tool libraries remains challenging due to two critical…

Artificial Intelligence · Computer Science 2026-04-15 Rongzhe Wei , Ge Shi , Min Cheng , Na Zhang , Pan Li , Sarthak Ghosh , Vaibhav Gorde , Leman Akoglu

This paper proposes EvoAgent - an evolvable large language model (LLM) agent framework that integrates structured skill learning with a hierarchical sub-agent delegation mechanism. EvoAgent models skills as multi-file structured capability…

Artificial Intelligence · Computer Science 2026-04-27 Aimin Zhang , Jiajing Guo , Fuwei Jia , Chen Lv , Boyu Wang , Fangzheng Li

The semiconductor industry faces a critical "Productivity Gap" where design complexity outpaces human capacity. While the "AI for EDA" revolution (L2) successfully optimized specific point problems, a paradigm shift toward Agentic EDA (L3)…

Systems and Control · Electrical Eng. & Systems 2026-02-10 Zelin Zang , Yuhang Song , Aili Wang , Bingo Wing-Kuen Ling , Qi Sun , Zhen Lei , Fuji Yang , Cheng Zhuo , Jiebo Luo

In this technical report we describe describe the Domain Specific Language (DSL) of the Workflow Execution Execution (WEE). Instead of interpreting an XML based workflow description language like BPEL, the WEE uses a minimized but…

Software Engineering · Computer Science 2010-03-18 Juergen Mangler , Gerhard Stuermer , Erich Schikuta

Smart contract vulnerabilities have led to significant financial losses, with their increasing complexity rendering outright prevention of hacks increasingly challenging. This trend highlights the crucial need for advanced forensic analysis…

Cryptography and Security · Computer Science 2025-04-15 Kaihua Qin , Zhe Ye , Zhun Wang , Weilin Li , Liyi Zhou , Chao Zhang , Dawn Song , Arthur Gervais

Multi-access edge computing (MEC) aims to extend cloud service to the network edge to reduce network traffic and service latency. A fundamental problem in MEC is how to efficiently offload heterogeneous tasks of mobile applications from…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-10-27 Jin Wang , Jia Hu , Geyong Min , Albert Y. Zomaya , Nektarios Georgalas

Attribute-Based Encryption (ABE) is a promising solution for access control in cloud services. However, the heavy decryption overhead hinders its widespread adoption. A general approach to address this issue is to outsource decryption to…

Cryptography and Security · Computer Science 2024-11-07 Dongliang Cai , Borui Chen , Liang Zhang , Kexin Li , Haibin Kan