Related papers: Springdrift: An Auditable Persistent Runtime for L…

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…

Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…

As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution…

Building and evaluating enterprise AI systems requires synthetic organizational corpora that are internally consistent, temporally structured, and cross-artifact traceable. Existing corpora either carry legal constraints or inherit…

Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However, most existing MLLMs perform reasoning primarily with textual CoT, which limits their…

We address the problem of runtime trajectory anomaly detection, a critical capability for enabling trustworthy LLM agents. Current safety measures predominantly focus on static input/output filtering. However, we argue that ensuring LLM…

Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that fail on semantically meaningful attacks or use static LLM-based detectors that struggle to…

Advanced Persistent Threats (APTs) are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit…

Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databases. While persistent…

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…

LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Existing work frames this as \emph{post-hoc…

Large Language Models (LLMs) excel at single-turn tasks such as instruction following and summarization, yet real-world deployments require sustained multi-turn interactions where user goals and conversational context persist and evolve. A…

LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks that elicit harmful behaviors without explicit policy violations. While a growing body of…

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…

Large language models (LLMs) can now translate a researcher's plain-language goal into executable computation, yet scientific workflows demand determinism, provenance, and governance that are difficult to guarantee when an LLM decides what…

Insider threats pose a significant challenge to organizational security, often evading traditional rule-based detection systems due to their subtlety and contextual nature. This paper presents an AI-powered Insider Risk Management (IRM)…

Background: LLMs enable patient-facing conversational agents, creating a pathway toward digital twins that capture older adults' lived experiences and behavioral responses across time. A central barrier is personality drift -- inconsistent…

Existing LLM-enabled multi-agent frameworks are predominantly limited to digital or simulated environments and confined to narrowly focused knowledge domain, constraining their applicability to complex engineering tasks that require the…

Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not…

Multi-agent reinforcement learning (MARL) demonstrates significant progress in solving cooperative and competitive multi-agent problems in various environments. One of the principal challenges in MARL is the need for explicit prediction of…