Related papers: ARACNE: An LLM-Based Autonomous Shell Pentesting A…
LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction. These agentic LLM inference tasks are fundamentally different from chatbot-focused…
We introduce Agent2 RL-Bench, a compact diagnostic benchmark for evaluating agentic RL post-training, which tests whether LLM agents can autonomously design, implement, debug, and execute post-training pipelines that improve foundation…
This paper explores the potential of a multidisciplinary approach to testing and aligning artificial intelligence (AI), specifically focusing on large language models (LLMs). Due to the rapid development and wide application of LLMs,…
As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via…
The proliferation of autonomous agents powered by large language models (LLMs) has revolutionized popular business applications dealing with tabular data, i.e., tabular agents. Although LLMs are observed to be vulnerable against prompt…
As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…
The integration of experimental technologies with large language models (LLMs) is transforming scientific research. It positions AI as a versatile research assistant rather than a mere problem-solving tool. In the field of power systems,…
Prompt injection attacks represent a major vulnerability in Large Language Model (LLM) deployments, where malicious instructions embedded in user inputs can override system prompts and induce unintended behaviors. This paper presents a…
Although Large Language Model (LLM)-based agents are increasingly used in financial trading, it remains unclear whether they can reason and adapt in live markets, as most studies test models instead of agents, cover limited periods and…
Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that…
Compilers are critical to modern computing, yet fixing compiler bugs is difficult. While recent large language model (LLM) advancements enable automated bug repair, compiler bugs pose unique challenges due to their complexity, deep…
LLM-based agents have shown promise in various cooperative and strategic reasoning tasks, but their effectiveness in competitive multi-agent environments remains underexplored. To address this gap, we introduce PillagerBench, a novel…
Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces…
Large language models (LLMs) have empowered intelligent agents to execute intricate tasks within domain-specific software such as browsers and games. However, when applied to general-purpose software systems like operating systems, LLM…
Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.…
Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge devices, it suffers from severe non-stationarity due to the…
Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We…
We introduce a novel reinforcement learning framework of LLM agents named AGILE (AGent that Interacts and Learns from Environments) designed to perform complex conversational tasks with users, leveraging LLMs, memory, tools, and…
We introduce AIRTBench, an AI red teaming benchmark for evaluating language models' ability to autonomously discover and exploit Artificial Intelligence and Machine Learning (AI/ML) security vulnerabilities. The benchmark consists of 70…
Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…