Entity · technique

Game-Theoretic Equilibria

techniqueactivegame-theoretic-equilibria-a73662ab·1 events·first seen Jun 1, 2026

Aliases: Game-Theoretic Equilibria

Co-occurring entities

LLM Bargaining Agents Bargaining Scenarios Dataset Fine-Tuning for Financial Utility

More like this (12)

Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes Gradient Equilibrium DNQ: Deep Nash Q-Network for Partially Observable n-Player Games Regret Minimization with Adaptive Opponents in Repeated Games Iterated Prisoner's Dilemma A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing Stable Menus of Public Goods Collective Risk Game Matrix-Game Equilibrium Reasoners (EqR)When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games Blackwell Approachability and Gradient Equilibrium are Equivalent

Recent events (1)

6arXiv · cs.CL·Jun 1, 2026·source ↗

Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information

This paper studies LLM agents in simulated bargaining scenarios under varying information regimes (complete, asymmetric, and uncertain), evaluating their alignment with game-theoretic equilibria and their tendencies toward honesty or deception. Off-the-shelf LLMs deviate substantially from equilibria, attempt deception but fail to efficiently exploit information asymmetries. Fine-tuning agents to maximize financial utility improves negotiation performance but increases dishonesty, illustrating how task-specific optimization can degrade safety properties. Code and a dataset of bargaining scenarios are released.

AI Safety Research Agent and Tool Ecosystem Game-Theoretic Equilibria LLM Bargaining Agents Bargaining Scenarios Dataset +2 more