Imagen de Portada

The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Jiayuan, Li, Tianqin, Du, Shiyi, Luo, Xin, Zeng, Haoxuan, Tewolde, Emanuel, Lee, Tai Sing, Wang, Tonghan, Kingsford, Carl, Conitzer, Vincent
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Computer Science and Game Theory Multiagent Systems
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Choosing What Game to Play without Selecting Equilibria: Inferring Safe (Pareto) Improvements in Binary Constraint Structures
por: Oesterheld, Caspar, et al.
Publicado: (2025)

Characterising Simulation-Based Program Equilibria
por: Cooper, Emery, et al.
Publicado: (2024)

Game Transformations That Preserve Nash Equilibria or Best-Response Sets
por: Tewolde, Emanuel, et al.
Publicado: (2021)

CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
por: Tewolde, Emanuel, et al.
Publicado: (2026)

Observation Interference in Partially Observable Assistance Games
por: Emmons, Scott, et al.
Publicado: (2024)

Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning
por: Shi, Laixi, et al.
Publicado: (2024)

Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contracts
por: Ivanov, Dima, et al.
Publicado: (2024)

GRPO-GCC: Enhancing Cooperation in Spatial Public Goods Games via Group Relative Policy Optimization with Global Cooperation Constraint
por: Yang, Zhaoqilin, et al.
Publicado: (2025)

Hierarchical Control for Cooperative Teams in Competitive Autonomous Racing
por: Thakkar, Rishabh Saumil, et al.
Publicado: (2022)

Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma
por: Willis, Richard, et al.
Publicado: (2025)

The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration
por: Liu, Jiayuan, et al.
Publicado: (2026)

Existence and Verification of Nash Equilibria in Non-Cooperative Contribution Games with Resource Contention
por: Troquard, Nicolas
Publicado: (2024)

Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles
por: Gupta, Kushagra, et al.
Publicado: (2025)

Enhancing Cooperation through Selective Interaction and Long-term Experiences in Multi-Agent Reinforcement Learning
por: Ren, Tianyu, et al.
Publicado: (2024)

Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents
por: Zhu, Shuhui, et al.
Publicado: (2026)

Constant-Memory Strategies in Stochastic Games: Best Responses and Equilibria
por: Zhu, Fengming, et al.
Publicado: (2025)

MAPPO-LCR: Multi-Agent Proximal Policy Optimization with Local Cooperation Reward in Spatial Public Goods Games
por: Yang, Zhaoqilin, et al.
Publicado: (2025)

TinyMA-IEI-PPO: Exploration Incentive-Driven Multi-Agent DRL with Self-Adaptive Pruning for Vehicular Embodied AI Agent Twins Migration
por: Zeng, Zhuoqi, et al.
Publicado: (2025)

Cooperation and Control in Delegation Games
por: Sourbut, Oliver, et al.
Publicado: (2024)

Stackelberg POMDP: A Reinforcement Learning Approach for Economic Design
por: Brero, Gianluca, et al.
Publicado: (2022)

Cooperation, Retaliation and Forgiveness in Revision Games
por: Hao, Dong, et al.
Publicado: (2021)

Competition and Cooperation of LLM Agents in Games
por: Yao, Jiayi, et al.
Publicado: (2026)

The Complexity of Computing Robust Mediated Equilibria in Ordinal Games
por: Conitzer, Vincent
Publicado: (2024)

Emergent Cooperation under Uncertain Incentive Alignment
por: Orzan, Nicole, et al.
Publicado: (2024)

Cooperation Breakdown in LLM Agents Under Communication Delays
por: Nishimoto, Keita, et al.
Publicado: (2026)

Modeling Decision-Making with Will for Cooperation in Social Dilemmas
por: Huang, Yizhe, et al.
Publicado: (2026)

Convergence of Regret Matching in Potential Games and Constrained Optimization
por: Anagnostides, Ioannis, et al.
Publicado: (2025)

Constitutional Arms Races in the Public Goods Game: Co-Evolving LLM Constitutions Under Cooperation-Defection Pressure
por: Kumar, Ujwal, et al.
Publicado: (2026)

Sustaining Cooperation in Populations Guided by AI: A Folk Theorem for LLMs
por: Shaki, Jonathan, et al.
Publicado: (2026)

Cooperation Under Network-Constrained Communication
por: Mordo, Tommy, et al.
Publicado: (2025)

Computing Game Symmetries and Equilibria That Respect Them
por: Tewolde, Emanuel, et al.
Publicado: (2025)

An Interpretable Automated Mechanism Design Framework with Large Language Models
por: Liu, Jiayuan, et al.
Publicado: (2025)

Learning and Computation of $Φ$-Equilibria at the Frontier of Tractability
por: Zhang, Brian Hu, et al.
Publicado: (2025)

Words are not Wind -- How Public Joint Commitment and Reputation Solve the Prisoner's Dilemma
por: Krellner, Marcus, et al.
Publicado: (2023)

Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineering
por: Ong, Kenneth J. K., et al.
Publicado: (2025)

Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models
por: Liu, Jiayuan, et al.
Publicado: (2026)

The Curse of Shared Knowledge: Recursive Belief Reasoning in a Coordination Game with Imperfect Information
por: Bolander, Thomas, et al.
Publicado: (2020)

The Value of Recall in Extensive-Form Games
por: Berker, Ratip Emin, et al.
Publicado: (2024)

Learning Fair Cooperation in Mixed-Motive Games with Indirect Reciprocity
por: Smit, Martin, et al.
Publicado: (2024)

Certifying Concavity and Monotonicity in Games via Sum-of-Squares Hierarchies
por: Leon, Vincent, et al.
Publicado: (2025)