Related papers: HunterAgent: Neuro-Symbolic Attack Trace Reconstru…

LLM Agents are becoming central to intelligent systems. However, their deployment raises serious safety concerns. Existing defenses largely rely on "Safety Checks", which struggle to capture the complex semantic risks posed by harmful user…

Large Language Models (LLMs) have been equipped with safety mechanisms to prevent harmful outputs, but these guardrails can often be bypassed through "jailbreak" prompts. This paper introduces a novel graph-based approach to systematically…

Large Language Model agents often retrieve context from knowledge bases that lack structural consistency with the agent's current reasoning state, leading to incoherent reasoning chains. We introduce Path-Constrained Retrieval (PCR), a…

Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting…

Automating legal reasoning forces a choice between imperfect alternatives: symbolic systems offer transparency but struggle with ambiguity, whereas neural systems handle natural language flexibly but lack verifiability. This paper…

Deploying capable and user-aligned LLM-based systems necessitates reliable evaluation. While LLMs excel in verifiable tasks like coding and mathematics, where gold-standard solutions are available, adoption remains challenging for…

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

Reliable detection of deceptive behavior in Large Language Model (LLM) agents is an essential prerequisite for safe deployment in high-stakes agentic contexts. Prior work on scheming detection has focused exclusively on black-box monitors…

The recent progress in multi-agent deep reinforcement learning(MADRL) makes it more practical in real-world tasks, but its relatively poor scalability and the partially observable constraints raise challenges to its performance and…

Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness but, more critically, by its stealthiness. However, existing…

Despite their remarkable success, large language models (LLMs) have shown limited ability on safety-critical code tasks such as vulnerability detection. Typically, static analysis (SA) tools, like CodeQL, CodeGuru Security, etc., are used…

Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended…

Automated structural defect annotation is essential for ensuring infrastructure safety while minimizing the high costs and inefficiencies of manual labeling. A novel agentic annotation framework, Agent-based Defect Pattern Tagger (ADPT), is…

Advanced Persistent Threats (APTs) have caused significant losses across a wide range of sectors, including the theft of sensitive data and harm to system integrity. As attack techniques grow increasingly sophisticated and stealthy, the…

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly deployed in industry applications, yet their reliability remains hampered by challenges in detecting hallucinations. While supervised…

Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already functions as…

Disruptions at critical logistics nodes pose severe risks to global supply chains, yet existing risk prediction systems typically prioritize forecasting accuracy without providing operationally interpretable early warnings. This paper…

Current document chunking methods for Retrieval-Augmented Generation (RAG) typically linearize text. This forced linearization strips away intrinsic topological hierarchies, creating ``semantic fragmentation'' that degrades downstream…

Large Language Models (LLMs) have shown promising results on various language and vision tasks. Recently, there has been growing interest in applying LLMs to graph-based tasks, particularly on Text-Attributed Graphs (TAGs). However, most…