English
Related papers

Related papers: Self-playing Adversarial Language Game Enhances LL…

200 papers

Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adaptive decision-making. However, existing self-play approaches…

Artificial Intelligence · Computer Science 2026-04-21 Xiachong Feng , Deyi Yin , Xiaocheng Feng , Yi Jiang , Libo Qin , Yangfan Ye , Lei Huang , Weitao Ma , Qiming Li , Yuxuan Gu , Bing Qin , Lingpeng Kong

Strategic reasoning enables agents to cooperate, communicate, and compete with other agents in diverse situations. Existing approaches to solving strategic games rely on extensive training, yielding strategies that do not generalize to new…

Artificial Intelligence · Computer Science 2023-05-31 Kanishk Gandhi , Dorsa Sadigh , Noah D. Goodman

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Computation and Language · Computer Science 2024-06-12 Fan Liu , Zhao Xu , Hao Liu

Over the past two years, the use of large language models (LLMs) has advanced rapidly. While these LLMs offer considerable convenience, they also raise security concerns, as LLMs are vulnerable to adversarial attacks by some well-designed…

Computation and Language · Computer Science 2025-04-24 Guang Lin , Toshihisa Tanaka , Qibin Zhao

Adversarial board games, as a paradigmatic domain of strategic reasoning and intelligence, have long served as both a popular competitive activity and a benchmark for evaluating artificial intelligence (AI) systems. Building on this…

Artificial Intelligence · Computer Science 2025-08-08 Yingjie Zhou , Jiezhang Cao , Farong Wen , Li Xu , Yanwei Jiang , Jun Jia , Ronghui Li , Xiaohong Liu , Yu Zhou , Xiongkuo Min , Jie Guo , Zicheng Zhang , Guangtao Zhai

The automatic evaluation of LLM-based agent intelligence is critical in developing advanced LLM-based agents. Although considerable effort has been devoted to developing human-annotated evaluation datasets, such as AlpacaEval, existing…

Computation and Language · Computer Science 2023-11-07 Tian Liang , Zhiwei He , Jen-tse Huang , Wenxuan Wang , Wenxiang Jiao , Rui Wang , Yujiu Yang , Zhaopeng Tu , Shuming Shi , Xing Wang

The standard Reinforcement Learning from Human Feedback (RLHF) framework primarily focuses on optimizing the performance of large language models using pre-collected prompts. However, collecting prompts that provide comprehensive coverage…

Computation and Language · Computer Science 2024-06-18 Rui Zheng , Hongyi Guo , Zhihan Liu , Xiaoying Zhang , Yuanshun Yao , Xiaojun Xu , Zhaoran Wang , Zhiheng Xi , Tao Gui , Qi Zhang , Xuanjing Huang , Hang Li , Yang Liu

Evaluating the social intelligence of Large Language Models (LLMs) increasingly requires moving beyond static text generation toward dynamic, adversarial interaction. We introduce the Adversarial Resource Extraction Game (AREG), a benchmark…

Computation and Language · Computer Science 2026-02-19 Adib Sakhawat , Fardeen Sadab

Evaluating the step-by-step reliability of large language model (LLM) reasoning, such as Chain-of-Thought, remains challenging due to the difficulty and cost of obtaining high-quality step-level supervision. In this paper, we introduce…

Computation and Language · Computer Science 2025-05-20 Jiaqi Chen , Bang Zhang , Ruotian Ma , Peisong Wang , Xiaodan Liang , Zhaopeng Tu , Xiaolong Li , Kwan-Yee K. Wong

This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents. Unlike augmenting LLMs with prompt engineering, Thinker…

Artificial Intelligence · Computer Science 2024-04-01 Shuang Wu , Liwen Zhu , Tao Yang , Shiwei Xu , Qiang Fu , Yang Wei , Haobo Fu

Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red…

Cryptography and Security · Computer Science 2026-01-16 Hao Wang , Yanting Wang , Hao Li , Rui Li , Lei Sha

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

Multiagent Systems · Computer Science 2026-05-12 Xiaolin Sun , Zixuan Liu , Yibin Hu , Zizhan Zheng

We study whether multiple large language models (LLMs) can autonomously improve each other in a negotiation game by playing, reflecting, and criticizing. We are interested in this question because if LLMs were able to improve each other, it…

Computation and Language · Computer Science 2023-05-18 Yao Fu , Hao Peng , Tushar Khot , Mirella Lapata

Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of actions, which is…

Artificial Intelligence · Computer Science 2025-05-30 Zelai Xu , Chao Yu , Fei Fang , Yu Wang , Yi Wu

In recent years, large language models (LLMs) have shown significant advancements in natural language processing (NLP), with strong capa-bilities in generation, comprehension, and rea-soning. These models have found applications in…

Artificial Intelligence · Computer Science 2025-04-02 Hui Wang

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Computation and Language · Computer Science 2024-05-03 Mansi Phute , Alec Helbling , Matthew Hull , ShengYun Peng , Sebastian Szyller , Cory Cornelius , Duen Horng Chau

Safety alignment is critical in pre-training large language models (LLMs) to generate responses aligned with human values and refuse harmful queries. Unlike LLM, the current safety alignment of VLMs is often achieved with post-hoc safety…

Cryptography and Security · Computer Science 2025-02-18 Fenghua Weng , Jian Lou , Jun Feng , Minlie Huang , Wenjie Wang

Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on static, pre-collected data distributions}. In this paper, we…

Artificial Intelligence · Computer Science 2026-02-09 Xiaoyu Wen , Zhida He , Han Qi , Ziyu Wan , Zhongtian Ma , Ying Wen , Tianhang Zheng , Xingcheng Xu , Chaochao Lu , Qiaosheng Zhang

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to…

Artificial Intelligence · Computer Science 2026-02-10 Anselm Paulus , Ilia Kulikov , Brandon Amos , Rémi Munos , Ivan Evtimov , Kamalika Chaudhuri , Arman Zharmagambetov

Traditional methods for raising awareness of privacy protection often fail to engage users or provide hands-on insights into how privacy vulnerabilities are exploited. To address this, we incorporate an adversarial mechanic in the design of…

Human-Computer Interaction · Computer Science 2025-05-23 Jiaying Fu , Yiyang Lu , Zehua Yang , Fiona Nah , RAY LC