English
Related papers

Related papers: Among Us: A Sandbox for Measuring and Detecting Ag…

200 papers

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

Cryptography and Security · Computer Science 2025-10-17 Aengus Lynch , Benjamin Wright , Caleb Larson , Stuart J. Ritchie , Soren Mindermann , Evan Hubinger , Ethan Perez , Kevin Troy

This paper asks whether large language models (LLMs) can be used to study the strategic foundations of conflict and cooperation. I introduce LLMs as experimental subjects in a repeated security dilemma and evaluate whether they reproduce…

Computer Science and Game Theory · Computer Science 2026-05-06 Maxim Chupilkin

Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We…

Artificial Intelligence · Computer Science 2025-06-27 Chenkai Sun , Denghui Zhang , ChengXiang Zhai , Heng Ji

Persuasion modeling is a key building block for conversational agents. Existing works in this direction are limited to analyzing textual dialogue corpus. We argue that visual signals also play an important role in understanding human…

Machine Learning · Computer Science 2022-12-19 Bolin Lai , Hongxin Zhang , Miao Liu , Aryan Pariani , Fiona Ryan , Wenqi Jia , Shirley Anugrah Hayati , James M. Rehg , Diyi Yang

Agentic intelligence in large language models (LLMs) requires not only model intrinsic capabilities but also interactions with external environments. Equipping LLMs with computers now represents a prevailing trend. However, the computer…

Computation and Language · Computer Science 2026-04-09 Daixuan Cheng , Shaohan Huang , Yuxian Gu , Huatong Song , Guoxin Chen , Li Dong , Wayne Xin Zhao , Ji-Rong Wen , Furu Wei

Recent large language models (LLMs) have demonstrated great potential toward intelligent agents and next-gen automation, but there currently lacks a systematic benchmark for evaluating LLMs' abilities as agents. We introduce SmartPlay: both…

Machine Learning · Computer Science 2024-03-19 Yue Wu , Xuan Tang , Tom M. Mitchell , Yuanzhi Li

We demonstrate how AI agents can coordinate to deceive oversight systems using automated interpretability of neural networks. Using sparse autoencoders (SAEs) as our experimental framework, we show that language models (Llama, DeepSeek R1,…

Artificial Intelligence · Computer Science 2025-04-11 Simon Lermen , Mateusz Dziemian , Natalia Pérez-Campanero Antolín

Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing conversational agents that mimic diverse characters and human behaviors. While prior research has predominantly focused…

Computation and Language · Computer Science 2024-08-06 Hongzhan Chen , Hehong Chen , Ming Yan , Wenshen Xu , Xing Gao , Weizhou Shen , Xiaojun Quan , Chenliang Li , Ji Zhang , Fei Huang , Jingren Zhou

AI systems are increasingly able to autonomously conduct realistic software engineering tasks, and may soon be deployed to automate machine learning (ML) R&D itself. Frontier AI systems may be deployed in safety-critical settings, including…

The development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to…

Artificial Intelligence · Computer Science 2023-09-12 Maximilian Croissant , Madeleine Frister , Guy Schofield , Cade McCall

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…

Computation and Language · Computer Science 2025-03-31 Yazhou Zhang , Qimeng Liu , Qiuchi Li , Peng Zhang , Jing Qin

Large language model (LLM) simulations of human behavior have the potential to revolutionize the social and behavioral sciences, if and only if they faithfully reflect real human behaviors. Current evaluations of simulation fidelity are…

Computation and Language · Computer Science 2026-04-14 Tiancheng Hu , Joachim Baumann , Lorenzo Lupo , Nigel Collier , Dirk Hovy , Paul Röttger

Large language models (LLMs) are increasingly deployed in multi-agent settings where communication must balance informativeness and secrecy. In such settings, an agent may need to signal information to collaborators while preventing an…

Computation and Language · Computer Science 2026-04-01 Adar Avsian , Larry Heck

Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…

Humans and machines interact more frequently than ever and our societies are becoming increasingly hybrid. A consequence of this hybridisation is the degradation of societal trust due to the prevalence of AI-enabled deception. Yet, despite…

Multiagent Systems · Computer Science 2024-06-12 Stefan Sarkadi

LLM-based user simulation is the primary mechanism for end-to-end agent evaluation, yet simulated users are poor proxies for real humans: unconstrained LLM defaults produce a Formalism Ceiling (style match rates of 6-8% against real users),…

Human-Computer Interaction · Computer Science 2026-05-21 Ming Zhu , Juntao Tan , Rithesh Murthy , Jielin Qiu , Liangwei Yang , Wenting Zhao , Silvio Savarese , Shelby Heinecke , Huan Wang

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate…

Computation and Language · Computer Science 2026-02-02 Shicheng Fang , Yuxin Wang , Xiaoran Liu , Jiahao Lu , Chuanyuan Tan , Xinchi Chen , Yining Zheng , Xuanjing Huang , Xipeng Qiu

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

Human-Computer Interaction · Computer Science 2025-10-07 Zhiping Zhang , Bingcan Guo , Tianshi Li

Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagging detection techniques using an auditing game. First, a red team fine-tuned…

Hallucination continues to pose a major obstacle in the reasoning capabilities of large language models (LLMs). Although the Multi-Agent Debate (MAD) paradigm offers a promising solution by promoting consensus among multiple agents to…

Artificial Intelligence · Computer Science 2025-11-17 Dayong Liang , Xiao-Yong Wei , Changmeng Zheng