Workerville: Towards an Organizational Behavior Account of Agent Safety

cs.AI

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/Astarojth/Workerville

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coordination
• S-Agents: Self-organizing Agents in Open-ended Environments
• Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
• Embodied LLM Agents Learn to Cooperate in Organized Teams
• Organizational Principles Enable Collective Intelligence in Embodied AI
• A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
• FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models
• BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models
• AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents
• AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters
• BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models
• AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning
• CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding
• PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?
• Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
• Generative Agents: Interactive Simulacra of Human Behavior
• AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
• Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems