Related papers: AgentSys: Secure and Dynamic LLM Agents Through Ex…

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…

Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal knowledge of LLMs to effortlessly translate complex tasks…

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and…

Memory is a critical component in large language model (LLM)-based agents, enabling them to store and retrieve past executions to improve task performance over time. In this paper, we conduct an empirical study on how memory management…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK…

LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a…

When large language model (LLM) systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker…

Persistent memory attacks against LLM agents achieve high attack success rates against open-source models. In these attacks, malicious instructions injected via RAG-retrieved documents are stored in persistent memory and executed in later…

Providing AI agents with reliable long-term memory that does not hallucinate remains an open problem. Current approaches to memory for LLM agents -- sliding windows, summarization, embedding-based RAG, and flat fact extraction -- each…

A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…

Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…

The emergence of LLM (Large Language Model) integrated virtual assistants has brought about a rapid transformation in communication dynamics. During virtual assistant development, some developers prefer to leverage the system message, also…

Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables autonomy, it also expands the attack surface for backdoor threats. Backdoor triggers…

Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition from static predictors to interactive systems capable of…

Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution quality, recent approaches deploy multiple agent teams running…

Large Language Models (LLMs) suffer from significant performance degradation when processing long contexts due to proactive interference, where irrelevant information in earlier parts of the context disrupts reasoning and memory recall.…

Large Language Model (LLM) agents struggle with long-horizon software engineering tasks due to "Context Bloat." As interaction history grows, computational costs explode, latency increases, and reasoning capabilities degrade due to…

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more…