English
Related papers

Related papers: GIFT: Games as Informal Training for Generalizable…

200 papers

Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language. To what extent can LLMs generalize across these…

Computation and Language · Computer Science 2026-02-04 Fangru Lin , Valentin Hofmann , Xingchen Wan , Weixing Wang , Zifeng Ding , Anthony G. Cohn , Janet B. Pierrehumbert

Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement…

Machine Learning · Computer Science 2025-04-22 Cheng Qian , Emre Can Acikgoz , Qi He , Hongru Wang , Xiusi Chen , Dilek Hakkani-Tür , Gokhan Tur , Heng Ji

Strategic decision-making involves interactive reasoning where agents adapt their choices in response to others, yet existing evaluations of large language models (LLMs) often emphasize Nash Equilibrium (NE) approximation, overlooking the…

Artificial Intelligence · Computer Science 2025-11-04 Jingru Jia , Zehua Yuan , Junhao Pan , Paul E. McNamara , Deming Chen

The rapid advancements in large language models (LLMs) have presented challenges in evaluating those models. Existing evaluation methods are either reference-based or preference based, which inevitably need human intervention or introduce…

Computation and Language · Computer Science 2023-08-22 Dan Qiao , Chenfei Wu , Yaobo Liang , Juntao Li , Nan Duan

Recent studies have investigated whether large language models (LLMs) can support obscured communication, which is characterized by core aspects such as inferring subtext and evading suspicions. To conduct the investigation, researchers…

Artificial Intelligence · Computer Science 2025-10-08 Byungjun Kim , Dayeon Seo , Minju Kim , Bugeun Kim

We introduce LLM CHESS, an evaluation framework designed to probe the generalization of reasoning and instruction-following abilities in large language models (LLMs) through extended agentic interaction in the domain of chess. We rank over…

Artificial Intelligence · Computer Science 2025-12-02 Sai Kolasani , Maxim Saplin , Nicholas Crispino , Kyle Montgomery , Jared Quincy Davis , Matei Zaharia , Chi Wang , Chenguang Wang

Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the…

Artificial Intelligence · Computer Science 2025-11-05 Sihao Hu , Tiansheng Huang , Gaowen Liu , Ramana Rao Kompella , Fatih Ilhan , Selim Furkan Tekin , Yichang Xu , Zachary Yahn , Ling Liu

Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges in using popular video games to evaluate modern LLMs and…

Artificial Intelligence · Computer Science 2025-06-04 Lanxiang Hu , Mingjia Huo , Yuxuan Zhang , Haoyang Yu , Eric P. Xing , Ion Stoica , Tajana Rosing , Haojian Jin , Hao Zhang

Previous work has shown that training "helpful-only" LLMs with reinforcement learning on a curriculum of gameable environments can lead models to generalize to egregious specification gaming, such as editing their own reward function or…

Artificial Intelligence · Computer Science 2024-10-10 Leo McKee-Reid , Christoph Sträter , Maria Angelica Martinez , Joe Needham , Mikita Balesni

As evaluation designs of large language models may shape our trajectory toward artificial general intelligence, comprehensive and forward-looking assessment is essential. Existing benchmarks primarily assess static knowledge, while…

Computation and Language · Computer Science 2025-08-07 Jiayin Wang , Zhiquang Guo , Weizhi Ma , Min Zhang

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

Computation and Language · Computer Science 2025-10-29 ChangSu Choi , Hoyun Song , Dongyeon Kim , WooHyeon Jung , Minkyung Cho , Sunjin Park , NohHyeob Bae , Seona Yu , KyungTae Lim

Large Language Models (LLMs) have demonstrated proficiency in utilizing various tools by coding, yet they face limitations in handling intricate logic and precise control. In embodied tasks, high-level planning is amenable to direct coding,…

Artificial Intelligence · Computer Science 2024-03-01 Shaoteng Liu , Haoqi Yuan , Minda Hu , Yanwei Li , Yukang Chen , Shu Liu , Zongqing Lu , Jiaya Jia

Previous research has sought to enhance the graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. While these led to specialized LLMs better at solving graph algorithm problems, we don't need LLMs for…

Machine Learning · Computer Science 2025-08-19 Yizhuo Zhang , Heng Wang , Shangbin Feng , Zhaoxuan Tan , Xinyun Liu , Yulia Tsvetkov

Large Language Models (LLMs) exhibit remarkable capabilities, yet it remains unclear to what extent these reflect sophisticated recall or genuine reasoning ability. We introduce chess as a controlled testbed aimed at disentangling these…

Computation and Language · Computer Science 2026-05-20 Leonard S. Pleiss , Maximilian Schiffer , Robert K. von Weizsaecker

Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through role-based orchestration, while RL uses environmental…

Machine Learning · Computer Science 2026-02-02 Yujie Zhao , Lanxiang Hu , Yang Wang , Minmin Hou , Hao Zhang , Ke Ding , Jishen Zhao

In aligning large language models (LLMs), reward models have played an important role, but are standardly trained as discriminative models and rely only on labeled human preference data. In this paper, we explore methods that train reward…

Computation and Language · Computer Science 2026-01-27 Chenglong Wang , Yang Gan , Yifu Huo , Yongyu Mu , Qiaozhi He , Murun Yang , Bei Li , Tong Xiao , Chunliang Zhang , Tongran Liu , Jingbo Zhu

Generalization in reinforcement learning (RL) is of importance for real deployment of RL algorithms. Various schemes are proposed to address the generalization issues, including transfer learning, multi-task learning and meta learning, as…

Machine Learning · Computer Science 2022-10-07 Chang Yang , Ruiyu Wang , Xinrun Wang , Zhen Wang

We present Frost Training, a method for improving Monte Carlo-based policy optimization for a large family of LLM-as-a-judge tasks called Cross-Entropy Games. The key idea is to exploit the gradient of the reward function in embedding…

Artificial Intelligence · Computer Science 2026-05-28 Arthur Renard , Franck Gabriel , Valentin Hartmann , Clément Hongler

Since the COVID-19 pandemic, educational institutions have embarked on digital transformation projects. The success of these projects depends on integrating new technologies and understanding the needs of digitally literate students. The…

Artificial Intelligence · Computer Science 2024-02-15 Rita Stampfl , Igor Ivkić , Barbara Geyer

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

Machine Learning · Computer Science 2025-11-25 Maxime Heuillet , Yufei Cui , Boxing Chen , Audrey Durand , Prasanna Parthasarathi