Related papers: Structured Security Auditing and Robustness Enhanc…
Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting and limited generalization. To address this, we propose a novel scaling paradigm that shifts the…
An agent skill is a configuration package that equips an LLM-driven agent with a concrete capability, such as reading email, executing shell commands, or signing blockchain transactions. Each skill is a hybrid artifact-a structured half…
Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines. Skills execute with user privileges and are distributed through community registries with minimal vetting, but no…
Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We…
Software supply chain attacks have revealed blind spots in existing SCA tools, which are often limited to a single ecosystem and assess either software artifacts or community activity in isolation. This fragmentation across tools and…
Optimistic rollups provide scalable smart-contract execution but remain unsuitable for regulated financial applications due to three structural gaps: semantic legitimacy, cross-layer state consistency, and ordering fairness. We introduce…
Equipping LLM agents with real-world tools can substantially improve productivity. However, granting agents autonomy over tool use also transfers the associated privileges to both the agent and the underlying LLM. Improper privilege usage…
Blockchain smart contracts have emerged as a transformative force in the digital realm, spawning a diverse range of compelling applications. Since solidity smart contracts across various domains manage trillions of dollars in virtual coins,…
Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only by semantic similarity. This leads to two key challenges for…
Large Language Model (LLM) agents are increasingly extended at runtime via skill packages, structured natural-language instruction bundles loaded from a well-known directory. Community install tooling and registries exist, but two gaps…
EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…
The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces…
Predicting and classifying faults in electricity networks is crucial for uninterrupted provision and keeping maintenance costs at a minimum. Thanks to the advancements in the field provided by the smart grid, several data-driven approaches…
Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically.…
Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill…
Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed by external teachers, hand-designed rules, or auxiliary…
Autonomous agents powered by foundation models have seen widespread adoption across various real-world applications. However, they remain highly vulnerable to malicious instructions and attacks, which can result in severe consequences such…
Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores,…
Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of…
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing…