Copertina

Emotional Cost Functions for AI Safety: Teaching Agents to Feel the Weight of Irreversible Consequences

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Mopgar, Pandurang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Do LLMs Feel? Teaching Emotion Recognition with Prompts, Retrieval, and Curriculum Learning
di: Li, Xinran, et al.
Pubblicazione: (2025)

Feeling Machines: Ethics, Culture, and the Rise of Emotional AI
di: Chavan, Vivek, et al.
Pubblicazione: (2025)

Teaching AI to Feel: A Collaborative, Full-Body Exploration of Emotive Communication
di: Tütüncü, Esen K., et al.
Pubblicazione: (2025)

AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries
di: Shu, Wesley, et al.
Pubblicazione: (2026)

Do LLMs "Feel"? Emotion Circuits Discovery and Control
di: Wang, Chenxi, et al.
Pubblicazione: (2025)

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
di: Vijayvargiya, Sanidhya, et al.
Pubblicazione: (2025)

Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models
di: Lin, Yuxiang, et al.
Pubblicazione: (2025)

Combining Cost-Constrained Runtime Monitors for AI Safety
di: Hua, Tim Tian, et al.
Pubblicazione: (2025)

What You Feel Is Not What They See: On Predicting Self-Reported Emotion from Third-Party Observer Labels
di: El-Tawil, Yara, et al.
Pubblicazione: (2026)

OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
di: Wen, Ming, et al.
Pubblicazione: (2026)

Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights
di: Andreux, Mathieu, et al.
Pubblicazione: (2025)

Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition
di: Xia, Haiying, et al.
Pubblicazione: (2025)

SafePro: Evaluating the Safety of Professional-Level AI Agents
di: Zhou, Kaiwen, et al.
Pubblicazione: (2026)

Building Altruistic and Moral AI Agent with Brain-inspired Emotional Empathy Mechanisms
di: Zhao, Feifei, et al.
Pubblicazione: (2024)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
di: Yuan, Youliang, et al.
Pubblicazione: (2024)

AgentWall: A Runtime Safety Layer for Local AI Agents
di: Aravind, Ashwin
Pubblicazione: (2026)

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents
di: Li, Miles Q., et al.
Pubblicazione: (2026)

Safeguarding AI Agents: Developing and Analyzing Safety Architectures
di: Domkundwar, Ishaan, et al.
Pubblicazione: (2024)

Offline Training of Language Model Agents with Functions as Learnable Weights
di: Zhang, Shaokun, et al.
Pubblicazione: (2024)

LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing
di: Di Palma, Dario, et al.
Pubblicazione: (2025)

Improving the Safety and Trustworthiness of Medical AI via Multi-Agent Evaluation Loops
di: Ghafoor, Zainab, et al.
Pubblicazione: (2026)

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
di: Yang, Chenglin
Pubblicazione: (2026)

Do You Feel Comfortable? Detecting Hidden Conversational Escalation in AI Chatbots
di: Park, Jihyung, et al.
Pubblicazione: (2025)

Limits to AI Growth: The Ecological and Social Consequences of Scaling
di: Bhardwaj, Eshta, et al.
Pubblicazione: (2025)

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
di: Yin, Lu, et al.
Pubblicazione: (2023)

BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments
di: Li, Yuxuan, et al.
Pubblicazione: (2026)

Robust Agent Compensation (RAC): Teaching AI Agents to Compensate
di: Perera, Srinath, et al.
Pubblicazione: (2026)

AI with Emotions: Exploring Emotional Expressions in Large Language Models
di: Ishikawa, Shin-nosuke, et al.
Pubblicazione: (2025)

Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval
di: Huang, Le, et al.
Pubblicazione: (2024)

TeachAnything: A Multimodal Crowdsourcing Platform for Training Embodied AI Agents in Symmetrical Reality
di: Liu, Zidong, et al.
Pubblicazione: (2026)

Simulating Human Behavior with the Psychological-mechanism Agent: Integrating Feeling, Thought, and Action
di: Dong, Qing, et al.
Pubblicazione: (2025)

Solution for Emotion Prediction Competition of Workshop on Emotionally and Culturally Intelligent AI
di: Xu, Shengdong, et al.
Pubblicazione: (2024)

DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents
di: Li, Qi, et al.
Pubblicazione: (2025)

The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
di: Overman, William, et al.
Pubblicazione: (2025)

Your Robot Will Feel You Now: Empathy in Robots and Embodied Agents
di: Lim, Angelica, et al.
Pubblicazione: (2026)

Generative AI Agents in Autonomous Machines: A Safety Perspective
di: Jabbour, Jason, et al.
Pubblicazione: (2024)

The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
di: Staufer, Leon, et al.
Pubblicazione: (2026)

Agentic AI Ecosystems in Higher Education: A Perspective on AI Agents to Emerging Inclusive, Agentic Multi-Agent AI Framework for Learning, Teaching and Institutional Intelligence
di: Sudarshan, Vidya K, et al.
Pubblicazione: (2026)

The Internet of Physical AI Agents: Interoperability, Longevity, and the Cost of Getting It Wrong
di: Morabito, Roberto, et al.
Pubblicazione: (2026)

Thermodynamic Irreversibility of Training Algorithms
di: Ziyin, Liu, et al.
Pubblicazione: (2026)