Buchumschlag

AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Covas, Vinicius, Toledo, Jorge Alberto Hidalgo
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language Artificial Intelligence Computers and Society Multiagent Systems
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Reimagining Urban Science: Scaling Causal Inference with Large Language Models
von: Xia, Yutong, et al.
Veröffentlicht: (2025)

AI Urban Scientist: Multi-Agent Collaborative Automation for Urban Research
von: Xia, Tong, et al.
Veröffentlicht: (2025)

Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
von: Kumar, Shivani, et al.
Veröffentlicht: (2026)

Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models
von: Choi, Younwoo, et al.
Veröffentlicht: (2025)

WorldView-Bench: A Benchmark for Evaluating Global Cultural Perspectives in Large Language Models
von: Mushtaq, Abdullah, et al.
Veröffentlicht: (2025)

LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
von: Frisch, Ivar, et al.
Veröffentlicht: (2024)

Collective Behavior of AI Agents: the Case of Moltbook
von: De Marzo, Giordano, et al.
Veröffentlicht: (2026)

Conformity Generates Collective Misalignment in AI Agents Societies
von: De Marzo, Giordano, et al.
Veröffentlicht: (2026)

Editing Personality for Large Language Models
von: Mao, Shengyu, et al.
Veröffentlicht: (2023)

Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming
von: Steenstra, Ian, et al.
Veröffentlicht: (2026)

When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis
von: Dietrich, Juergen
Veröffentlicht: (2026)

Escalation Risks from Language Models in Military and Diplomatic Decision-Making
von: Rivera, Juan-Pablo, et al.
Veröffentlicht: (2024)

Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective
von: Gabison, Garry A., et al.
Veröffentlicht: (2025)

Food4All: A Multi-Agent Framework for Real-time Free Food Discovery with Integrated Nutritional Metadata
von: Yuan, Zhengqing, et al.
Veröffentlicht: (2025)

Emergent Social Intelligence Risks in Generative Multi-Agent Systems
von: Huang, Yue, et al.
Veröffentlicht: (2026)

LLM-Based Social Simulations Require a Boundary
von: Wu, Zengqing, et al.
Veröffentlicht: (2025)

Transforming Competition into Collaboration: The Revolutionary Role of Multi-Agent Systems and Language Models in Modern Organizations
von: Cruz, Carlos Jose Xavier
Veröffentlicht: (2024)

Fake Plastic Voters: When Political Parties Can Use AI-Simulated Focus Groups
von: Novelli, Claudio, et al.
Veröffentlicht: (2026)

Enhancing Collective Intelligence in Large Language Models Through Emotional Integration
von: Kadiyala, Likith, et al.
Veröffentlicht: (2025)

Incorporating LLMs for Large-Scale Urban Complex Mobility Simulation
von: Song, Yu-Lun, et al.
Veröffentlicht: (2025)

Preserving Cultural Identity with Context-Aware Translation Through Multi-Agent AI Systems
von: Anik, Mahfuz Ahmed, et al.
Veröffentlicht: (2025)

Using Large Language Models to Simulate Human Behavioural Experiments: Port of Mars
von: Slumbers, Oliver, et al.
Veröffentlicht: (2025)

RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models
von: Khaliq, M. Abdul, et al.
Veröffentlicht: (2024)

Mechanism Plausibility in Generative Agent-Based Modeling
von: Zhao, Patrick, et al.
Veröffentlicht: (2026)

Multi-User Large Language Model Agents
von: Yang, Shu, et al.
Veröffentlicht: (2026)

Nature-Inspired Population-Based Evolution of Large Language Models
von: Zhang, Yiqun, et al.
Veröffentlicht: (2025)

AI-Supported Platform for System Monitoring and Decision-Making in Nuclear Waste Management with Large Language Models
von: Chang, Dongjune, et al.
Veröffentlicht: (2025)

Research on Comprehensive Classroom Evaluation System Based on Multiple AI Models
von: Xie, Cong, et al.
Veröffentlicht: (2025)

Cross-Document Contextual Coreference Resolution in Knowledge Graphs
von: Dong, Zhang, et al.
Veröffentlicht: (2025)

Using Feasible Action-Space Reduction by Groups to fill Causal Responsibility Gaps in Spatial Interactions
von: Guenov, Vassil, et al.
Veröffentlicht: (2026)

Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles
von: Zeng, Yongchao, et al.
Veröffentlicht: (2025)

Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design
von: Musi, Elena, et al.
Veröffentlicht: (2025)

Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
von: Choi, Hyeong Kyu, et al.
Veröffentlicht: (2025)

LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
von: Agashe, Saaket, et al.
Veröffentlicht: (2023)

Integration of Large Vision Language Models for Efficient Post-disaster Damage Assessment and Reporting
von: Chen, Zhaohui, et al.
Veröffentlicht: (2024)

Computational Foundations for Strategic Coopetition: Formalizing Collective Action and Loyalty
von: Pant, Vik, et al.
Veröffentlicht: (2026)

Psychologically Enhanced AI Agents
von: Besta, Maciej, et al.
Veröffentlicht: (2025)

Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
von: White, Isadora, et al.
Veröffentlicht: (2025)

Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach
von: Huang, Tianyi, et al.
Veröffentlicht: (2024)

Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closeness
von: Sakamoto, Yuki, et al.
Veröffentlicht: (2025)