相关论文: In-Context Defense in Computer Agents: An Empirica…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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,…

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…

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…

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…