Image de couverture de livre

What Suppresses Nash Equilibrium Play in Large Language Models? Mechanistic Evidence and Causal Control

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lekeas, Paraskevas V., Stamatopoulos, Giorgos
Format:	Preprint
Publié:	2026
Sujets:	Computer Science and Game Theory Artificial Intelligence Machine Learning 91A10, 68T07 I.2.6; I.2.11; J.4
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
par: Pepe, Alberto, et autres
Publié: (2026)

Territory Paint Wars: Diagnosing and Mitigating Failure Modes in Competitive Multi-Agent PPO
par: Singh, Diyansha
Publié: (2026)

Adaptive Latent-Space Constraints in Personalized Federated Learning
par: Ayromlou, Sana, et autres
Publié: (2025)

On the Fundamental Limitations of Decentralized Learnable Reward Shaping in Cooperative Multi-Agent Reinforcement Learning
par: Akella, Aditya
Publié: (2025)

Decentralized Time Series Classification with ROCKET Features
par: Casella, Bruno, et autres
Publié: (2025)

A Theory of Multilevel Interactive Equilibrium in NeuroAI
par: Chen, Zhe Sage, et autres
Publié: (2026)

Emergent Coordination in Multi-Agent Systems via Pressure Fields and Temporal Decay
par: Rodriguez, Roland
Publié: (2026)

The Coordination Gap: Multi-Agent Alternation Metrics for Temporal Fairness in Repeated Games
par: Papadopoulos, Nikolaos Al., et autres
Publié: (2026)

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
par: Tang, Wenjie, et autres
Publié: (2026)

DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas
par: Wang, Zhen, et autres
Publié: (2025)

Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
par: Jing, Yuheng, et autres
Publié: (2026)

Generating Realistic Safety-Critical Scenarios for Vehicle-Pedestrian Interactions
par: Pu, Qingwen, et autres
Publié: (2026)

AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems
par: Liu, Hung Ming
Publié: (2025)

Safe Distributed Control of Multi-Robot Systems with Communication Delays
par: Ballotta, Luca, et autres
Publié: (2024)

Learning to Manipulate under Limited Information
par: Holliday, Wesley H., et autres
Publié: (2024)

Your Data, My Model: Learning Who Really Helps in Federated Learning
par: Abdurakhmanova, Shamsiiat, et autres
Publié: (2024)

Dynamic Dual-Granularity Skill Bank for Agentic RL
par: Tu, Songjun, et autres
Publié: (2026)

Generative Evolutionary Meta-Solver (GEMS): Scalable Surrogate-Free Multi-Agent Reinforcement Learning
par: Sharma, Alakh, et autres
Publié: (2025)

Evaluation of Differential Privacy Mechanisms on Federated Learning
par: Varsani, Tejash
Publié: (2025)

More at Stake: How Payoff and Language Shape LLM Agent Strategies in Cooperation Dilemmas
par: Huynh, Trung-Kiet, et autres
Publié: (2026)

DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game
par: Chen, Xiaobing, et autres
Publié: (2024)

Privacy as Commodity: MFG-RegretNet for Large-Scale Privacy Trading in Federated Learning
par: Sun, Kangkang, et autres
Publié: (2026)

Online Federation For Mixtures of Proprietary Agents with Black-Box Encoders
par: Yang, Xuwei, et autres
Publié: (2025)

When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
par: Chowdhury, Arindam, et autres
Publié: (2025)

Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences
par: Hosseini, Hadi, et autres
Publié: (2025)

Coopetition-Gym v1: A Formally Grounded Platform for Mixed-Motive Multi-Agent Reinforcement Learning under Strategic Coopetition
par: Pant, Vik, et autres
Publié: (2026)

How to Correctly do Semantic Backpropagation on Language-based Agentic Systems
par: Wang, Wenyi, et autres
Publié: (2024)

The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
par: Pal, Biplab, et autres
Publié: (2026)

AI Agents: Evolution, Architecture, and Real-World Applications
par: Krishnan, Naveen
Publié: (2025)

Adaptive Minds: Empowering Agents with LoRA-as-Tools
par: Shekar, Pavan C, et autres
Publié: (2025)

Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games
par: Qi, Runnan, et autres
Publié: (2025)

The Axiom of Consent: Friction Dynamics in Multi-Agent Coordination
par: Farzulla, Murad
Publié: (2026)

RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
par: Ashley, Dylan R., et autres
Publié: (2026)

Client-Conditional Federated Learning via Local Training Data Statistics
par: Brännvall, Rickard
Publié: (2026)

Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
par: Soumalias, Ermis, et autres
Publié: (2024)

Super-Nash Performance
par: Ismail, Mehmet S.
Publié: (2019)

PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation
par: Wang, Yuchen, et autres
Publié: (2026)

Mean-Field Reinforcement Learning without Synchrony
par: Yang, Shan
Publié: (2026)

Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions
par: Alpay, Faruk, et autres
Publié: (2025)

BEHAVE: A Hybrid AI Framework for Real-Time Modeling of Collective Human Dynamics
par: Malyutina, Helene
Publié: (2026)