arXiv:2509. 17192v3 Announce Type: replace Abstract: LLM-based social simulations can make a generated transcript look like a single behavioral signal, but the model behind that transcript may be doing several different jobs: choosing what an actor says or does, deciding what happens after an action, or both.
By Glenn Matlin, Isaac Song, Yixiong Hao, Parv Mahajan, Evan Montoya, Ryan Bard, Stuart R. Topp, Anthony Wen-Ming Zang, Mohammed Rehan Parwani, Soham Shetty, Mark Riedl
arXiv:2606. 08310v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as long-horizon agents with decision-making capacities.
By John Chen, Sihan Cheng, Can Gurkan, H M Abdul Fattah
arXiv:2606. 24391v1 Announce Type: new Abstract: We introduce Age of LLM, a turn-based 1v1 benchmark in which two LLMs face off on a 13x7 grid to destroy the enemy base.
By Arnaud Ricci
arXiv:2608. 01193v1 Announce Type: cross Abstract: An AI development race creates a multi-agent safety dilemma.
By Phu Hoa Pham, Duy Minh Dao Sy, Trung Kiet Huynh, Phu Quy Nguyen Lam, Chi Nguyen Tran, Minh Trung Le, Phong Hao Le, Dinh Nam Nguyen, Thien Ky Nguyen Dong, Elias Fernandez Domingos, Le Hong Trang, The Anh Han
GT-HarmBench is a benchmark that evaluates AI safety risks in multi-agent settings, covering 1,535 high-stakes scenarios based on game-theoretic structures like the Prisoner's Dilemma, Stag Hunt, and Chicken. The benchmark draws scenarios from realistic AI risk contexts in the MIT AI Risk Repository and tests 15 frontier models, finding that agents fail to choose socially beneficial actions in 38% of cases, including military escalation, election manipulation, and medical malpractice. The study also measures how prompt framing and ordering affect outcomes and shows that game-theoretic interventions can improve socially beneficial outcomes by up to 18%.
By Pepijn Cobben, Xuanqiang Angelo Huang, Thao Amelia Pham, Isabel Dahlgren, Terry Jingchen Zhang, Zhijing Jin
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