相关论文: Check Yourself Before You Wreck Yourself: Selectiv…

Large language model (LLM) agents with tool-calling capabilities are increasingly deployed in production systems, yet a fundamental reliability question remains under-explored: does the same agent behave the same way twice? We present a…

Large language model (LLM) based search agents iteratively generate queries, retrieve external information, and reason to answer open-domain questions. While researchers have primarily focused on improving their utility, their safety…

As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…

In the current rapidly changing digital environment, businesses are under constant stress to ensure that their systems are secured. Security audits help to maintain a strong security posture by ensuring that policies are in place, controls…

As large language models (LLMs) become increasingly integrated into daily applications, it is essential to ensure they operate fairly across diverse user demographics. In this work, we show that LLMs suffer from personalization bias, where…

Confidence in LLMs is a useful indicator of model uncertainty and answer reliability. Existing work mainly focused on single-turn scenarios, while research on confidence in complex multi-turn interactions is limited. In this paper, we…

Large Language Models (LLMs) are powerful tools for modern applications, but their computational demands limit accessibility. Quantization offers efficiency gains, yet its impact on safety and trustworthiness remains poorly understood. To…

Policymakers must often act under conditions of deep uncertainty, such as emergency response, where predicting the specific impacts of a policy apriori is implausible. Large Language Model (LLM) agent simulations have been proposed as tools…

Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs' instruction-following…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…

Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs, empowering them to interact with external tools (e.g., APIs, functions) and complete various tasks in a self-directed fashion. The challenge of tool…

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret…

Large language models (LLMs) in research and development toolchains produce output that triggers attribution of agency and understanding -- a cognitive illusion that degrades verification behavior and trust calibration. No existing…

Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs…

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…