Image de couverture de livre

Intentional Deception as Controllable Capability in LLM Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Starace, Jason, Soule, Terence
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Ethical Implications of Training Deceptive AI
par: Starace, Jason, et autres
Publié: (2026)

Behavioral Inference at Scale: The Fundamental Asymmetry Between Motivations and Belief Systems
par: Starace, Jason, et autres
Publié: (2025)

LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
par: Olson, Matthew Lyle, et autres
Publié: (2026)

Jailbreaking Frontier Foundation Models Through Intention Deception
par: Wang, Xinhe, et autres
Publié: (2026)

Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents
par: Xia, Feifan, et autres
Publié: (2025)

An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning
par: Soulé, Julien, et autres
Publié: (2025)

AI Deception: Risks, Dynamics, and Controls
par: Chen, Boyuan, et autres
Publié: (2025)

Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities
par: Anurin, Andrey, et autres
Publié: (2024)

Unmasking the Shadows of AI: Investigating Deceptive Capabilities in Large Language Models
par: Guo, Linge
Publié: (2024)

Enhancing Agent Safety Judgment: Controlled Benchmark Rewriting and Analogical Reasoning for Deceptive Out-of-Distribution Scenarios
par: Zhang, Zuoyu, et autres
Publié: (2026)

The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents
par: Liu, Yuhan, et autres
Publié: (2024)

OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation
par: Wu, Yichen, et autres
Publié: (2025)

Towards a Multi-Agent Simulation of Cyber-attackers and Cyber-defenders Battles
par: Soulé, Julien, et autres
Publié: (2025)

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows
par: Ming, Yifei, et autres
Publié: (2025)

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
par: Li, Xiangyi, et autres
Publié: (2026)

A Framework for Analyzing Abnormal Emergence in Service Ecosystems Through LLM-based Agent Intention Mining
par: Shen, Yifan, et autres
Publié: (2025)

Automating Deception: Scalable Multi-Turn LLM Jailbreaks
par: Kumarappan, Adarsh, et autres
Publié: (2025)

WOLF: Werewolf-based Observations for LLM Deception and Falsehoods
par: Agarwal, Mrinal, et autres
Publié: (2025)

Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems
par: Xie, Yizhe, et autres
Publié: (2025)

Deception at Scale: Deceptive Designs in 1K LLM-Generated Ecommerce Components
par: Chen, Ziwei, et autres
Publié: (2025)

CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation
par: Sinha, Aarush, et autres
Publié: (2026)

XBOUND: Exploring Capability Boundaries of Device-Control Agents at the State Level
par: Zhang, Shaoqing, et autres
Publié: (2025)

The Reasons that Agents Act: Intention and Instrumental Goals
par: Ward, Francis Rhys, et autres
Publié: (2024)

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
par: Lin, Minhua, et autres
Publié: (2026)

Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
par: Motwani, Sumeet Ramesh, et autres
Publié: (2024)

Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces
par: Zhang, Yilin, et autres
Publié: (2026)

The Traitors: Deception and Trust in Multi-Agent Language Model Simulations
par: Curvo, Pedro M. P.
Publié: (2025)

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
par: Lee, Seunghyun, et autres
Publié: (2026)

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
par: Probst, Benjamin, et autres
Publié: (2026)

It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers
par: Cho, Yong-eun
Publié: (2026)

Quantifying Frontier LLM Capabilities for Container Sandbox Escape
par: Marchand, Rahul, et autres
Publié: (2026)

D-Mem: A Dual-Process Memory System for LLM Agents
par: You, Zhixing, et autres
Publié: (2026)

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
par: Yu, Ye, et autres
Publié: (2026)

Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent
par: Haji, Fatemeh, et autres
Publié: (2024)

Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
par: Wu, Zhaomin, et autres
Publié: (2025)

Streamlining Resilient Kubernetes Autoscaling with Multi-Agent Systems via an Automated Online Design Framework
par: Soulé, Julien, et autres
Publié: (2025)

Structured Personality Control and Adaptation for LLM Agents
par: Wang, Jinpeng, et autres
Publié: (2026)

Intentional Gesture: Deliver Your Intentions with Gestures for Speech
par: Liu, Pinxin, et autres
Publié: (2025)

Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems
par: Peigne-Lefebvre, Pierre, et autres
Publié: (2025)

Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
par: Zhang, Guoxi, et autres
Publié: (2026)