Related papers: NASimEmu: Network Attack Simulator & Emulator for …

We propose a new framework for building and evaluating machine learning algorithms. We argue that many real-world problems require an agent which must quickly learn to respond to demands, yet can continue to perform and respond to new…

Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory…

Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community. Large language models (LLMs) are considered a promising foundation to build such agents…

This paper aims to propose a novel deep learning-integrated framework for deriving reliable simulation input models through incorporating multi-source information. The framework sources and extracts multisource data generated from…

AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

Simulation agents are essential for designing and testing systems that interact with humans, such as autonomous vehicles (AVs). These agents serve various purposes, from benchmarking AV performance to stress-testing system limits, but all…

Training agents to act in embodied environments typically requires vast training data or access to accurate simulation, neither of which exists for many cases in the real world. Instead, world models are emerging as an alternative…

Recently, large language model based (LLM-based) agents have been widely applied across various fields. As a critical part, their memory capabilities have captured significant interest from both industrial and academic communities. Despite…

Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

The integration of external tools is pivotal for empowering Large Language Model (LLM) agents with real-world capabilities. However, training these agents through direct, continuous interaction with diverse tools is often prohibitively…

As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential. However, reported benchmark scores often jointly reflect model capability and the implementation choices each benchmark is…

The rise of large language models (LLMs) has sparked a surge of interest in agents, leading to the rapid growth of agent frameworks. Agent frameworks are software toolkits and libraries that provide standardized components, abstractions,…

Processing-in-memory (PIM) has shown extraordinary potential in accelerating neural networks. To evaluate the performance of PIM accelerators, we present an ISA-based simulation framework including a dedicated ISA targeting neural networks…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Background and motivation: Combining Deep Reinforcement Learning (Deep RL) and Health Systems Simulations has significant potential, for both research into improving Deep RL performance and safety, and in operational practice. While…

We introduce Meta MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. This is the first Gym environment for machine learning (ML) tasks, enabling research on reinforcement…

Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks through interactions with environments, tools, and APIs. LM agents are primarily built with prompt engineering or supervised…

Deterministic electromagnetic (EM) simulators provide accurate radio propagation modeling but often require expert configuration and lack interactive flexibility. We present RadioSim Agent, an agentic framework that integrates large…