Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on complex, long-horizon tasks. While monolithic prompt engineering and stateless tool-calling paradigms struggle to scale, the field is rapidly converging toward \emph{agen...
Sanket Badhe, D. Shah, Priyanka Tiwari et al.· 0 citations
A unified systems foundation and reference architecture for the agentic skills ecosystem is established, formalize skills as externalized procedural knowledge bridging high-level cognitive planning with deterministic execution environments, and systematically delineate the architecture across a nine-stage lifecycle.
Sanket Badhe, D. Shah, Priyanka Tiwari et al.· 0 citations
SkillSec-Eval is presented, a lifecycle-aware framework for systematically evaluating the security of reusable agent skills and demonstrates that vulnerabilities arise at multiple lifecycle stages beyond execution, highlighting the need for lifecycle-aware security analysis of reusable agent skills.
The results demonstrate that explicit execution state is an effective and architecture-agnostic abstraction for scalable long-horizon agent skills, and improves task accuracy while substantially reducing cumulative token consumption.
