English
Related papers

Related papers: Trace-Level Analysis of Information Contamination …

200 papers

The prevailing assumption in agent orchestration is that more context is better. We test this on multi-agent software design across 10 tasks, 7 context-injection conditions, and over 2,700 runs, and find a crossover effect: the same…

Artificial Intelligence · Computer Science 2026-05-07 Saranyan Vigraham

Workplace toxicity is widely recognized as detrimental to organizational culture, yet quantifying its direct impact on operational efficiency remains methodologically challenging due to the ethical and practical difficulties of reproducing…

Artificial Intelligence · Computer Science 2026-04-28 Benedikt Mangold

This paper introduces a signature-based framework for detecting advertising creative fatigue using path signatures, a geometric representation from rough path theory. Creative fatigue -- the degradation of creative effectiveness under…

Applications · Statistics 2026-04-28 Charles Shaw

TRUST Agents is a collaborative multi-agent framework for explainable fact verification and fake news detection. Rather than treating verification as a simple true-or-false classification task, the system identifies verifiable claims,…

Artificial Intelligence · Computer Science 2026-04-15 Gautama Shastry Bulusu Venkata , Santhosh Kakarla , Maheedhar Omtri Mohan , Aishwarya Gaddam

We introduce PATHWAYS, a benchmark of 250 multi-step decision tasks that test whether web-based agents can discover and correctly use hidden contextual information. Across both closed and open models, agents typically navigate to relevant…

Artificial Intelligence · Computer Science 2026-02-17 Shifat E. Arman , Syed Nazmus Sakib , Tapodhir Karmakar Taton , Nafiul Haque , Shahrear Bin Amin

Agentic memory enables LLMs to persist information beyond a single context window and reuse it in later decisions, but it also introduces a new vulnerability: spurious correlations, where retrieved memory carries miscorrelated evidence and…

Machine Learning · Computer Science 2026-05-12 Luoxi Tang , Rupali Rajendra Vaje , Yuqiao Meng , Sakshi Sunil Narkar , Weicheng Ma , Zeyu Ding , Dazheng Zhang , Zhaohan Xi

In recent years, a significant research effort has been devoted to the design of distributed protocols for the control of multi-agent systems, as the scale and limited communication bandwidth characteristic of such systems render…

Multiagent Systems · Computer Science 2021-06-09 Rohit Konda , Rahul Chandan , Jason R. Marden

Large language models can generate runnable software artifacts, but their security remains difficult to evaluate end to end. This study examines that problem through a Detect--Repair--Verify (DRV) workflow, in which vulnerabilities are…

Software Engineering · Computer Science 2026-03-26 Cheng Cheng

Patient education materials for solid-organ transplantation vary substantially across U.S. centers, yet no systematic method exists to quantify this heterogeneity at scale. We introduce a framework that grounds the same patient questions in…

Information Retrieval · Computer Science 2026-03-24 Yubo Li , Ramayya Krishnan , Rema Padman

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these…

Artificial Intelligence · Computer Science 2026-05-29 Martin Odersky , Yaoyu Zhao , Yichen Xu , Oliver Bračevac , Cao Nguyen Pham

Computer Use Agents (CUAs), autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise environments. These agents introduce novel attack surfaces and…

Large language models are increasingly being assembled into medical multi-agent systems that emulate multidisciplinary consultation through specialist roles, peer review and consensus formation. In clinical decision support, however,…

Computation and Language · Computer Science 2026-05-28 Yinghao Zhu , Lei Gu , Zixiang Wang , Haoran Sang , Dehao Sui , Wen Tang , Lan Mi , Yasha Wang , Junyi Gao , Liang Yao , Tianfan Fu , Ewen Harrison , Lequan Yu , Liantao Ma

Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse reasoning and iterative refinement. However, these systems remain vulnerable to error…

Multiagent Systems · Computer Science 2026-05-21 Yong Jin Chun , Iftekhar Ahmed

As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…

Artificial Intelligence · Computer Science 2026-03-24 Gregory M. Ruddell

Multi-agent collaboration has emerged as a pivotal paradigm for addressing complex, distributed tasks in large language model (LLM)-driven applications. While prior research has focused on high-level architectural frameworks, the granular…

Multiagent Systems · Computer Science 2025-05-20 Haochun Wang , Sendong Zhao , Jingbo Wang , Zewen Qiang , Bing Qin , Ting Liu

As Large Language Models (LLMs) are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust between processing stages become a practical concern. This paper presents a…

Cryptography and Security · Computer Science 2025-11-03 Dominik Schwarz

Machine consciousness evaluations mostly see behavior. For language model agents that behavior is language and tool use. That lets an agent say the right things about itself even when the constraints that should make those statements matter…

Artificial Intelligence · Computer Science 2026-03-11 Elija Perrier , Michael Timothy Bennett

The growing adoption of IT-systems for modeling and executing (business) processes or services has thrust the scientific investigation towards techniques and tools which support more complex forms of process analysis. Many of them, such as…

Artificial Intelligence · Computer Science 2017-06-02 Riccardo De Masellis , Chiara Di Francescomarino , Chiara Ghidini , Sergio Tessaris

Information flow properties express the capability for an agent to infer information about secret behaviours of a partially observable system. In a language-theoretic setting, where the system behaviour is described by a language, we define…

Cryptography and Security · Computer Science 2014-09-04 Béatrice Bérard , John Mullins

The complexity of the operating environment and required technologies for highly automated driving is unprecedented. A different type of threat to safe operation besides the fault-error-failure model by Laprie et al. arises in the form of…

Artificial Intelligence · Computer Science 2023-03-08 Roman Gansch , Ahmad Adee