The paper investigates why large language models (LLMs) struggle in strategic decision-making under incomplete information. It identifies two key gaps: an observation‑belief gap where LLMs’ internal representations of game states are accurate but brittle, and a belief‑action gap where converting these internal beliefs into actions is weak, leading to suboptimal payoffs. Experiments with Llama 3.1, Qwen3, and gpt‑oss confirm that acting optimally on decoded beliefs would improve outcomes in most games, highlighting a bottleneck in belief‑to‑action conversion.
By Jan Sobotka, Mustafa O. Karabag, Ufuk Topcu
arXiv:2607. 00155v1 Announce Type: new Abstract: We study runtime human oversight of an AI agent when private information runs in both directions: the human privately knows her reward function, while the AI privately knows the quality of the action it proposes.
By Yunjin Tong
arXiv:1908.08773v3 Announce Type: replace
Abstract: In certain reinforcement learning (RL) scenarios there are adversaries trying to interfere with the underlying reward process for their own benefit...
By Victor Gallego, Roi Naveiro, David Rios Insua, David Gomez-Ullate Oteiza
arXiv:2604. 15267v2 Announce Type: replace-cross Abstract: It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive games such as the prisoner's dilemma and public goods settings.
By Emanuel Tewolde, Xiao Zhang, David Guzman Piedrahita, Vincent Conitzer, Zhijing Jin
arXiv:2608. 03958v1 Announce Type: new Abstract: As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles governing their collective behavior is essential for ensuring safety and cooperation.
By Alexander Meulemans, Maciej Wo{\l}czyk, Marissa A. Weis, Rajai Nasser, Roberta Rocca, Seijin Kobayashi, Guillaume Lajoie, Angelika Steger, Blake Richards, Marcus Hutter, James Manyika, Rif A. Saurous, Jo\~ao Sacramento, Blaise Ag\"uera y Arcas
arXiv:2510. 10813v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation.
By Enric Junque de Fortuny, Veronica Roberta Cappelli
arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
By Yoshua Bengio, Oliver Richardson, Tom\'a\v{s} Gaven\v{c}iak, Michael Cohen, Rory Svarc, Damiano Fornasiere, Gael Gendron, David Hyland, Aton Kamanda, Adam Oberman, Francis Rhys Ward, Anna Gaven\v{c}iak, Jacob Livingston Slosser, Vincent Mai, Iulian Serban, Joumana Ghosn
arXiv:2608. 15868v1 Announce Type: new Abstract: This paper presents CoupVisor, a decision-support system for the hidden-information card game Coup.
By Cris Huynh
arXiv:2607. 14641v1 Announce Type: new Abstract: Abductive reasoning operates in two directions.
By Remo Pareschi
The paper investigates whether in-context learning (ICL) in large language model agents reflects genuine recursive reasoning or simply statistical extrapolation. By testing LLM agents in a public goods game with manipulated historical feedback, the authors compare decision quality to a rational expectations equilibrium benchmark. They find that disrupting historical patterns eliminates the benefits of longer context, especially in highly interdependent settings, indicating that ICL behavior aligns more with statistical extrapolation than strategic reasoning.
By Yu Liu, Wenwen Li, Yifan Dou, Guangnan Ye
arXiv:2602. 20804v2 Announce Type: replace Abstract: Cooperative multi-agent reinforcement learning (MARL) is typically framed as a decentralised partially observable Markov decision process (Dec-POMDP), a setting whose hardness stems from two key challenges: partial observability and decentralised coordination.
By Kale-ab Tessera, Leonard Hinckeldey, Riccardo Zamboni, David Abel, Amos Storkey
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.