Welfare Regard in Multi-Agent Systems
cs.MA, cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/NousResearch/pokemon-agent
Terminology
Sources
- The feasibility of artificial consciousness through the lens of neuroscience
- Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values
- Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation
- Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
- Could a Large Language Model be Conscious?
- Reasoning Models Don't Always Say What They Think
- The Artificial Self: Characterising the landscape of AI identity
- When can we trust untrusted monitoring? A safety case sketch across collusion strategies
- AI Control: Improving Safety Despite Intentional Subversion
- Multi-Agent Risks from Advanced AI
- Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
- Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation
- Taking AI Welfare Seriously
- Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulation
- LLM Evaluators Recognize and Favor Their Own Generations
- Towards Evaluating AI Systems for Moral Status Using Self-Reports
- Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
- Peer-Preservation in Frontier Models
- Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations
Related papers
- MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
- Iterative Negotiation and Oversight: A Case Study in Decentralized Air Traffic Management
- Towards using Large Language Models for Risk Negotiation and Consensus-building in One Health contexts
- A-MapReduce: Executing Wide Search via Agentic MapReduce
- AgentCue: Statistical Summaries for Guiding Decentralized Multi-Agent Self-Organization
- Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning