Imagen de Portada

Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget Sensitivity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Rashidi, Mohammadreza
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Artificial Intelligence Machine Learning K.6.5; I.2.6; I.2.11
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
por: Tang, Wenjie, et al.
Publicado: (2026)

Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI
por: Pasupuleti, Vinil, et al.
Publicado: (2026)

Multi-Agent Honeypot-Based Request-Response Context Dataset for Improved SQL Injection Detection Performance
por: Yu, Hao, et al.
Publicado: (2026)

FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning
por: Zhang, Su, et al.
Publicado: (2026)

ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation
por: Mittal, Tarun
Publicado: (2026)

Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents
por: Ravindran, Santhosh Kumar
Publicado: (2026)

Sensitivity Uncertainty Alignment in Large Language Models
por: Hiremath, Prakul Sunil, et al.
Publicado: (2026)

Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
por: Lauffer, Niklas, et al.
Publicado: (2025)

Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning
por: Castellini, Jacopo, et al.
Publicado: (2019)

ME-IGM: Individual-Global-Max in Maximum Entropy Multi-Agent Reinforcement Learning
por: Chen, Wen-Tse, et al.
Publicado: (2024)

LLM Scalability Risk for Agentic-AI and Model Supply Chain Security
por: Ahi, Kiarash, et al.
Publicado: (2026)

Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory
por: Jiang, Rongjie, et al.
Publicado: (2026)

Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice
por: Ge, Yuxu
Publicado: (2026)

Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
por: Costa, Rimom
Publicado: (2025)

Learning To Help: Training Models to Assist Legacy Devices
por: Wu, Yu, et al.
Publicado: (2024)

StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context
por: Annapureddy, Sasank, et al.
Publicado: (2026)

One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents
por: Hong, Yoosung
Publicado: (2026)

David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement Learning
por: Nellessen, Samuel, et al.
Publicado: (2026)

PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation
por: Wang, Yuchen, et al.
Publicado: (2026)

When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines
por: Maryanskyy, Artem
Publicado: (2026)

Integrating Anomaly Detection into Agentic AI for Proactive Risk Management in Human Activity
por: Zorriassatine, Farbod, et al.
Publicado: (2026)

Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study
por: Xu, Luyao, et al.
Publicado: (2026)

Extending NGU to Multi-Agent RL: A Preliminary Study
por: Hernandez, Juan, et al.
Publicado: (2025)

N-Agent Ad Hoc Teamwork
por: Wang, Caroline, et al.
Publicado: (2024)

Inferring Communities of Interest in Collaborative Learning-based Recommender Systems
por: Belal, Yacine, et al.
Publicado: (2023)

FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
por: Zhang, Mingda, et al.
Publicado: (2026)

QTypeMix: Enhancing Multi-Agent Cooperative Strategies through Heterogeneous and Homogeneous Value Decomposition
por: Fu, Songchen, et al.
Publicado: (2024)

Latent Cache Flow: Model-to-Model Communication Without Text
por: Rossi, Maximillian, et al.
Publicado: (2026)

Risk-Sensitive Multi-Agent Reinforcement Learning in Network Aggregative Markov Games
por: Ghaemi, Hafez, et al.
Publicado: (2024)

Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)
por: Young, Richard J., et al.
Publicado: (2026)

Adaptive Minds: Empowering Agents with LoRA-as-Tools
por: Shekar, Pavan C, et al.
Publicado: (2025)

A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines
por: Du, Gaoyuan, et al.
Publicado: (2026)

Illuminating the Black Box: Real-Time Monitoring of Backdoor Unlearning in CNNs via Explainable AI
por: Hoang, Tien Dat
Publicado: (2025)

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults
por: Usman, Rana Muhammad
Publicado: (2026)

Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependence
por: Zhang, Yintong, et al.
Publicado: (2024)

Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents
por: Jehu-Appiah, Rodney
Publicado: (2026)

Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-agent AI Systems
por: Cai, Yicheng, et al.
Publicado: (2026)

PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
por: Schipper, Olivier, et al.
Publicado: (2025)

Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias
por: Wu, Shuai, et al.
Publicado: (2026)

Knowledge Equivalence in Digital Twins of Intelligent Systems
por: Zhang, Nan, et al.
Publicado: (2022)