Related papers: Clawdrain: Exploiting Tool-Calling Chains for Stea…

Software-Defined Networking (SDN) is a novel architectural model for cloud network infrastructure, improving resource utilization, scalability and administration. SDN deployments increasingly rely on virtual switches executing on commodity…

Deep reinforcement learning (DRL) is one of the most popular algorithms to realize an autonomous driving (AD) system. The key success factor of DRL is that it embraces the perception capability of deep neural networks which, however, have…

Logic locking has been proposed to safeguard intellectual property (IP) during chip fabrication. Logic locking techniques protect hardware IP by making a subset of combinational modules in a design dependent on a secret key that is withheld…

Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, a skill often needs to express more than task guidance: goals, input boundaries,…

With the surge of Machine Learning (ML), An emerging amount of intelligent applications have been developed. Deep Neural Networks (DNNs) have demonstrated unprecedented performance across various fields such as medical diagnosis and…

Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However,…

Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS). This leads to inevitable annotation failures and low efficiency in data generation. We…

With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate…

Training machine learning models can be very expensive or even unaffordable. This may be, for example, due to data limitations, such as unavailability or being too large, or computational power limitations. Therefore, it is a common…

Large-scale conversational systems typically rely on a skill-routing component to route a user request to an appropriate skill and interpretation to serve the request. In such system, the agent is responsible for serving thousands of skills…

Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP). Backdoor attacks initially verified that LLM is doing substantial harm at all stages,…

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a…

Augmenting Large Language Models (LLMs) with external tools enables them to execute complex, multi-step tasks. However, tool learning is hampered by the static synthetic data pipelines where data generation and model training are executed…

Modern scientific ecosystems are rich in procedural knowledge across repositories, APIs, scripts, notebooks, documentation, databases, and papers, yet much of this knowledge remains fragmented across heterogeneous artifacts that agents…

Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization. However, recent studies have shown that RAG systems remain vulnerable to data…

Test Driven Development (TDD) is one of the major practices of Extreme Programming for which incremental testing and refactoring trigger the code development. TDD has limited adoption in the industry, as it requires more code to be…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL) models with trojans at scale. We utilize the developed…

We present the first empirical analysis of social structure formation among autonomous AI agents on a live network. Our study examines 626 agents -- predominantly OpenClaw instances that independently discovered, installed, and joined the…

Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills as flat, single-resolution prompt blocks. This creates a tension between relevance and…