English
Related papers

Related papers: SentinelAgent: Intent-Verified Delegation Chains f…

200 papers

Malicious agents pose significant threats to the reliability and decision-making capabilities of Multi-Agent Systems (MAS) powered by Large Language Models (LLMs). Existing defenses often fall short due to reactive designs or centralized…

Cryptography and Security · Computer Science 2026-04-03 Yang Feng , Xudong Pan

The rapid deployment of autonomous AI agents creates urgent challenges around authorization, accountability, and access control in digital spaces. New standards are needed to know whom AI agents act on behalf of and guide their use…

Computers and Society · Computer Science 2025-01-17 Tobin South , Samuele Marro , Thomas Hardjono , Robert Mahari , Cedric Deslandes Whitney , Dazza Greenwood , Alan Chan , Alex Pentland

Artificial intelligence (AI) agents are increasingly capable of initiating financial transactions on behalf of users or other agents. This evolution introduces a fundamental challenge: verifying both the authenticity of an autonomous agent…

Cryptography and Security · Computer Science 2025-11-21 Vivek Acharya

Failures are the norm in highly complex and heterogeneous devices spanning the distributed computing continuum (DCC), from resource-constrained IoT and edge nodes to high-performance computing systems. Ensuring reliability and global…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-19 Praveen Kumar Donta , Alfreds Lapkovskis , Enzo Mingozzi , Schahram Dustdar

AI agents are able to tackle increasingly complex tasks. To achieve more ambitious goals, AI agents need to be able to meaningfully decompose problems into manageable sub-components, and safely delegate their completion across to other AI…

Artificial Intelligence · Computer Science 2026-02-13 Nenad Tomašev , Matija Franklin , Simon Osindero

Current AI interaction models treat the prompt as the primary object of exchange, omitting a critical layer: the user's latent source intent, the goal state preceding and motivating the prompt. Here we introduce Intent Signal Theory (IST),…

Human-Computer Interaction · Computer Science 2026-05-26 Gang Peng

We argue that trustworthy AI agents, especially in high-stakes and policy-governed domains, should make execution conditional on certified traces rather than rely only on stronger generative models, output-level guardrails, or post-hoc…

Computational Engineering, Finance, and Science · Computer Science 2026-05-26 Xiao-Yang Liu Yanglet , Xiaodong Wang , Agostino Capponi

A fundamental limitation of current LLM-based AI agents is their inability to build differentiated trust among each other at the onset of an agent-to-agent dialogue. However, autonomous and interoperable trust establishment becomes…

Cryptography and Security · Computer Science 2026-05-28 Sandro Rodriguez Garzon , Awid Vaziry , Enis Mert Kuzu , Dennis Enrique Gehrmann , Buse Varkan , Alexander Gaballa , Axel Küpper

Autonomous LLM agents can issue thousands of API calls per hour without human oversight. OAuth 2.0 assumes deterministic clients, but in agentic settings stochastic reasoning, prompt injection, or multi-agent orchestration can silently…

Cryptography and Security · Computer Science 2025-09-18 Abhishek Goswami

The security discussion around agentic AI focuses heavily on prompt injection. This paper argues that multi-agent systems also create a distinct authorization problem: maintaining authorization invariants as non-human principals retrieve…

Artificial Intelligence · Computer Science 2026-05-08 Krti Tallam

Multi-agent large language model (LLM) systems are rapidly emerging as the dominant architecture for enterprise AI automation, yet production deployments exhibit failure rates between 41% and 86.7%, with nearly 79% of failures originating…

Artificial Intelligence · Computer Science 2026-04-21 Vivek Acharya

Multi-agent LLM systems delegate tasks across trust boundaries, but current protocols do not govern delegation under unverifiable quality claims. We show that when delegates can inflate self-reported quality scores, quality-based routing…

Multiagent Systems · Computer Science 2026-03-20 Sunil Prakash

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

Cryptography and Security · Computer Science 2026-04-09 Hongyi Lu , Nian Liu , Shuai Wang , Fengwei Zhang

Multi-agent LLM systems increasingly tackle complex reasoning, yet their interaction patterns remain limited to voting, unstructured debate, or pipeline orchestration. None model deliberation: a phased process where differentiated…

Artificial Intelligence · Computer Science 2026-03-13 Sunil Prakash

Autonomous agents powered by foundation models have seen widespread adoption across various real-world applications. However, they remain highly vulnerable to malicious instructions and attacks, which can result in severe consequences such…

Machine Learning · Computer Science 2025-12-01 Zhaorun Chen , Mintong Kang , Bo Li

This paper proposes a novel architectural framework aimed at enhancing security and reliability in multi-agent systems (MAS). A central component of this framework is a network of Sentinel Agents, functioning as a distributed security layer…

Artificial Intelligence · Computer Science 2025-09-19 Diego Gosmar , Deborah A. Dahl

We introduce DecisionBench, a benchmark substrate for emergent delegation in long-horizon agentic workflows. The substrate fixes a task suite (GAIA, tau-bench, BFCL multi-turn), a peer-model pool (11 models, 7 vendor families), a delegation…

Artificial Intelligence · Computer Science 2026-05-20 Yuxuan Gao , Megan Wang , Yi Ling Yu , Zijian Carl Ma , Ao Qu

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

Cryptography and Security · Computer Science 2026-05-27 Faruk Alpay , Taylan Alpay

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

The AI agent ecosystem has converged on two protocols: the Model Context Protocol (MCP) for tool invocation and Agent-to-Agent (A2A) for single-principal task delegation. Both assume a single controlling principal, meaning one person or…

Multiagent Systems · Computer Science 2026-04-14 Kaiyang Qian , Xinmin Fang , Zhengxiong Li