Related papers: SkCC: Portable and Secure Skill Compilation for Cr…
Agent skills are modular instruction packages that combine YAML metadata, natural language instructions, and embedded code, and they have reached 196K publicly available instances, yet no mechanism exists to detect clone relationships among…
LLM agents benefit from reusable skills, yet test-time tasks often require guidance more specific than a static skill library can provide. We propose \emph{SkillTTA}, a Test-Time Adaptive Skill Synthesis method that retrieves a small set of…
Code synthesis, which requires a deep understanding of complex natural language problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests,…
GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code generation. However, the semantic and structural differences between these IRs create…
Fine-grained skill representations, commonly referred to as knowledge components (KCs), are fundamental to many approaches in student modeling and learning analytics. However, KC-level correctness labels are rarely available in real-world…
Compartmentalization is good security-engineering practice. By breaking a large software system into mutually distrustful components that run with minimal privileges, restricting their interactions to conform to well-defined interfaces, we…
Recent advances in large language models (LLMs) have substantially enhanced automated code generation across a wide range of programming languages. Nonetheless, verifying the correctness and executability of LLM-generated code remains a…
Agent skills extend local AI agents, such as Claude Code or Open Claw, with additional functionality, and their popularity has led to the emergence of dedicated skill marketplaces, similar to app stores for mobile applications.…
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment; this makes them susceptible to prompt injections when dealing with untrusted data. To overcome this limitation, we propose…
As code large language models (LLMs) evolve into tool-interactive agents via the Model Context Protocol (MCP), their generalization is increasingly limited by low-quality synthetic data and the diminishing returns of quantity scaling.…
The transition from monolithic large language models (LLMs) to modular, skill-equipped agents represents a fundamental architectural shift in artificial intelligence deployment. While general-purpose models demonstrate remarkable breadth in…
Cloud-native software delivery platforms orchestrate releases through complex, multi-stage pipelines composed of dozens of independently versioned tasks. When code is promoted between environments -- development to staging, staging to…
In the challenging field of introductory programming, high enrollments and failure rates drive us to explore tools and systems to enhance student outcomes, especially automated tools that scale to large cohorts. This paper presents and…
Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for…
Spatially-Coupled (SC)-LDPC codes are known to have outstanding error-correction performance and low decoding latency. Whereas previous works on LDPC and SC-LDPC codes mostly take either an asymptotic or a finite-length design approach, in…
Large Language Models (LLMs) such as GPT-4 and Llama have shown remarkable capabilities in a variety of software engineering tasks. Despite the advancements, their practical deployment faces challenges, including high financial costs, long…
While the benefits of reconfigurable manufacturing systems (RMS) are well-known, there are still challenges to their development, including, among others, a modular software architecture that enables rapid reconfiguration without much…
The design of post-quantum cryptography (PQC) hardware is a complex and hierarchical process with many challenges. A primary bottleneck is the conversion of PQC reference codes from C to high-level synthesis (HLS) specifications, which…
Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, not for interpretation by language models. For small models (4B-14B), this protocol…
Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that…