English
Related papers

Related papers: In-Context Defense in Computer Agents: An Empirica…

200 papers

Communication topology is a critical factor in the utility and safety of LLM-based multi-agent systems (LLM-MAS), making it a high-value intellectual property (IP) whose confidentiality remains insufficiently studied. Existing topology…

Cryptography and Security · Computer Science 2026-03-20 Zixun Xiong , Gaoyi Wu , Lingfeng Yao , Miao Pan , Xiaojiang Du , Hao Wang

While vision-language models (VLMs) have demonstrated remarkable performance across various tasks combining textual and visual information, they continue to struggle with fine-grained visual perception tasks that require detailed…

Computation and Language · Computer Science 2025-11-12 Zhehao Zhang , Ryan Rossi , Tong Yu , Franck Dernoncourt , Ruiyi Zhang , Jiuxiang Gu , Sungchul Kim , Xiang Chen , Zichao Wang , Nedim Lipka

The emergence of agent-to-agent communication protocols mirrors the early internet: powerful connectivity with minimal security infrastructure. When AI agents communicate on behalf of users, every message crosses a trust boundary where the…

Cryptography and Security · Computer Science 2026-03-03 Sahar Abdelnabi , Amr Gomaa , Eugene Bagdasarian , Per Ola Kristensson , Reza Shokri

Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify…

Artificial Intelligence · Computer Science 2025-10-13 Guangya Wan , Mingyang Ling , Xiaoqi Ren , Rujun Han , Sheng Li , Zizhao Zhang

Large Language Models (LLMs) have emerged as formidable instruments capable of comprehending and producing human-like text. This paper explores the potential of LLMs, to shape user perspectives and subsequently influence their decisions on…

Artificial Intelligence · Computer Science 2024-09-04 Ganesh Prasath Ramani , Shirish Karande , Santhosh V , Yash Bhatia

In this paper, we extend previous work on distributed reasoning using Contextual Defeasible Logic (CDL), which enables decentralised distributed reasoning based on a distributed knowledge base, such that the knowledge from different…

Artificial Intelligence · Computer Science 2020-10-02 Helio H. L. C. Monte-Alto , Mariela Morveli-Espinoza , Cesar A. Tacla

Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens of thousands of tokens. This saturates context limits and increases computational cost…

In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies have shown that PLMs are vulnerable to attacks from…

Computation and Language · Computer Science 2024-02-06 Shuguang Chen , Leonardo Neves , Thamar Solorio

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…

Artificial Intelligence · Computer Science 2024-12-06 Xuying Li , Zhuo Li , Yuji Kosuga , Yasuhiro Yoshida , Victor Bian

Large Language Model (LLM) agents trained with reinforcement learning (RL) show great promise for solving complex, multi-step tasks. However, their performance is often crippled by "Context Explosion", where the accumulation of long text…

Computation and Language · Computer Science 2025-12-16 Xuanzhang Liu , Jianglun Feng , Zhuoran Zhuang , Junzhe Zhao , Maofei Que , Jieting Li , Dianlei Wang , Hao Tong , Ye Chen , Pan Li

Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. We consider this as a new type of adversarial attack in NLP,…

Current LLM agents typically lack instance-level context, which comprises concrete facts such as environment structure, system configurations, and local mechanics. Consequently, existing methods are forced to intertwine exploration with…

Computation and Language · Computer Science 2026-01-14 Kuntai Cai , Juncheng Liu , Xianglin Yang , Zhaojie Niu , Xiaokui Xiao , Xing Chen

Large language model (LLM) agents increasingly rely on external tools and retrieval systems to autonomously complete complex tasks. However, this design exposes agents to indirect prompt injection (IPI), where attacker-controlled context…

Cryptography and Security · Computer Science 2026-02-27 Tian Zhang , Yiwei Xu , Juan Wang , Keyan Guo , Xiaoyang Xu , Bowen Xiao , Quanlong Guan , Jinlin Fan , Jiawei Liu , Zhiquan Liu , Hongxin Hu

A common problem for agents operating in real-world environments is that the response of an environment to their actions may be non-deterministic and observed through noise. This renders environmental state and progress towards completing a…

Artificial Intelligence · Computer Science 2024-05-21 William E Bishop , Alice Li , Christopher Rawles , Oriana Riva

Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Tommaso Galliena , Stefano Rosa , Tommaso Apicella , Pietro Morerio , Alessio Del Bue , Lorenzo Natale

Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction…

Cryptography and Security · Computer Science 2026-02-10 Ruoyao Wen , Hao Li , Chaowei Xiao , Ning Zhang

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Cryptography and Security · Computer Science 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

Vision Language Model (VLM)-based agents are stateful, autonomous entities capable of perceiving and interacting with their environments through vision and language. Multi-agent systems comprise specialized agents who collaborate to solve a…

Multiagent Systems · Computer Science 2025-08-14 Yutong Wu , Jie Zhang , Yiming Li , Chao Zhang , Qing Guo , Nils Lukas , Tianwei Zhang

Advances in the use of cognitive and machine learning (ML) enabled systems fuel the quest for novel approaches and tools to support software developers in executing their tasks. First, as software development is a complex and dynamic…

Software Engineering · Computer Science 2021-02-11 Glaucia Melo , Paulo Alencar , Donald Cowan

Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…

Computation and Language · Computer Science 2022-11-22 Jaechul Roh , Minhao Cheng , Yajun Fang