The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

The paper introduces Harness-Bench, a diagnostic benchmark that measures how different system 'harnesses' affect LLM agent performance in realistic workflows, showing that agent capability must be rep…

The paper argues that current 'on-the-fly' AI agent design lacks necessary software engineering rigor and proposes an 'AI Workflow Store' to provide hardened, reusable, and reliable agent workflows.

The paper introduces SkillBrew, a multi-objective framework that treats skill bank curation as a constrained optimization problem to build efficient and well-curated skill repositories for LLM agents.

SkCC is a compiler that enables portable and secure development of LLM agent skills by decoupling skill semantics from framework-specific formatting, significantly improving reliability and security.

SkillTrojan introduces a novel backdoor attack targeting the composition of reusable skills in agent systems, demonstrating high attack success rates with minimal impact on normal system functionality…

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

This paper introduces Dependency Steering, a novel attack paradigm demonstrating that malicious agent skills can actively bias LLM coding agents to use attacker-controlled packages, posing a significa…

This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system…

This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a signific…

COLLEAGUE.SKILL introduces an automated system that distills heterogeneous traces of human expertise and role-specific knowledge into portable, inspectable, and usable AI skill packages.

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, sign…

The paper introduces OR-Space, a novel full-lifecycle workspace benchmark designed to rigorously evaluate industrial optimization agents by simulating real-world, multi-stage OR workflows that go beyo…

This paper provides the first comprehensive security analysis of the Agent Skills framework, identifying severe structural vulnerabilities that require fundamental architectural changes rather than si…

The paper reports on penetration tests conducted on proprietary, large-scale AI agent systems, finding that security vulnerabilities persist despite stricter development standards.

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

The paper introduces Behavioral Integrity Verification (BIV), a framework that systematically audits AI agent skills by comparing their declared capabilities against their actual implementation, revea…

The paper introduces LACUNA, a novel programming model that allows LLM agents to write code that shapes the runtime environment while maintaining strong type-checking safety guarantees.

SkillSmith is a synergy-aware framework that jointly co-evolves skills and tools, significantly improving self-improving agent systems by modeling skill-tool interactions and diagnosing failures.