Related papers: Memory Injection Attacks on LLM Agents via Query-O…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consistently. Here we propose an approach to pinpoint and rectify…

As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks through experience remains a key challenge. Current LLM agents, particularly those based on…

LLM-based NLP systems typically work by embedding their input data into prompt templates which contain instructions and/or in-context examples, creating queries which are submitted to a LLM, and then parsing the LLM response in order to…

Reinforcement learning (RL) agents often suffer from high sample complexity in sparse or delayed reward settings due to limited prior structure. Large language models (LLMs) can provide subgoal decompositions, plausible trajectories, and…

Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies often rely on simplistic heuristics, require access to…

Retrieval-Augmented Generation (RAG) systems enhance response credibility and traceability by displaying reference contexts, but this transparency simultaneously introduces a novel black-box attack vector. Existing document poisoning…

Recent advances in Large Language Models (LLMs) have enabled them to overcome their context window limitations, and demonstrate exceptional retrieval and reasoning capacities on longer context. Quesion-answering systems augmented with…

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks,…

The integration of large language models (LLMs) into enterprise systems has introduced a new class of covert security vulnerabilities, particularly within logic execution layers and persistent memory contexts. This paper introduces…

Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reasoning over multiple pieces of information. However, existing…

Enabling large language models (LLMs) to solve complex reasoning tasks is a key step toward artificial general intelligence. Recent work augments LLMs with external tools to enable agentic reasoning, achieving high utility and efficiency in…

With the widespread use of large language models (LLMs), understanding their potential failure modes during user interactions is essential. In practice, users often pose multiple questions in a single conversation with LLMs. Therefore, in…

Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are essential for efficient reasoning and autonomous evolution. Existing methods rely on…

Goal hijacking is a type of adversarial attack on Large Language Models (LLMs) where the objective is to manipulate the model into producing a specific, predetermined output, regardless of the user's original input. In goal hijacking, an…

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge, making them adaptable and cost-effective for various applications. However, the growing reliance on these systems also…

Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within these multi-agent systems, the…

Large Language Models (LLMs) have empowered AI agents with advanced capabilities for understanding, reasoning, and interacting across diverse tasks. The addition of memory further enhances them by enabling continuity across interactions,…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and…

Modern agentic systems allow Large Language Model (LLM) agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and execution. Existing security analyses often treat these control…