Related papers: SkCC: Portable and Secure Skill Compilation for Cr…

Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve…

Agent skills extend large language model (LLM) agents with reusable, program-like modules that define triggering conditions, procedural logic, and tool interactions. As these skills proliferate in public marketplaces, it is unclear what…

Scilla is a higher-order polymorphic typed intermediate level language for implementing smart contracts. In this talk, we describe a Scilla compiler targeting LLVM, with a focus on mapping Scilla types, values, and its functional language…

Fast machine code generation is especially important for fast start-up just-in-time compilation, where the compilation time is part of the end-to-end latency. However, widely used compiler frameworks like LLVM do not prioritize fast…

Large Language Models (LLMs) have improved programming efficiency, but their performance degrades significantly as requirements scale; when faced with multi-modal documents containing hundreds of scenarios, LLMs often produce incorrect…

Large language models (LLMs) have revolutionized code generation, significantly enhancing developer productivity. However, for a vast number of users with minimal coding knowledge, LLMs provide little support, as they primarily generate…

Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…

Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited…

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can even degrade it. Existing methods still treat skill injection as a static step, selecting…

With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for augmenting agent capabilities. However, these marketplaces face unprecedented security…

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…

We investigate how to elicit compositional generalization capabilities in large language models (LLMs). Compositional generalization empowers LLMs to solve complex problems by combining foundational skills, a critical reasoning ability akin…

The reasoning capabilities of the recent LLMs enable them to execute external function calls to overcome their inherent limitations, such as knowledge cutoffs, poor arithmetic skills, or lack of access to private data. This development has…

Security Operations Centers (SOCs) face mounting operational challenges. These challenges come from increasing threat volumes, heterogeneous SIEM platforms, and time-consuming manual triage workflows. We present an end-to-end threat…

The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill…

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…

Compilers, while essential, are notoriously complex systems that demand prohibitively expensive human expertise to develop and maintain. The recent advancements in Large Language Models (LLMs) offer a compelling new paradigm: Neural…

The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however,…

Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks…