When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs
cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Entropy-Lens: Uncovering Decision Strategies in LLMs
- Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
- Multi-Agent Risks from Advanced AI
- Social physics in the age of artificial intelligence
- Media and responsible AI governance: a game-theoretic and LLM analysis
- Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma
- How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis
- Latent Collaboration in Multi-Agent Systems
- Preventing Language Models From Hiding Their Reasoning
- Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
- Emergent Multi-Agent Communication in the Deep Learning Era
- Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation
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