The paper introduces DBA-Bench, a benchmark for evaluating database agents with production fidelity, outcome-first evaluation, and controlled scenario reproducibility.

The paper introduces EnterpriseClawBench, an enterprise agent benchmark with 852 tasks and evaluation protocol, achieving a best configuration score of 0.663.

This paper introduces CAGE-1, an evaluation framework for deciding the readiness of enterprise agents for deployment, focusing on control, assurance, and governance.

This paper proposes a dynamic capability scoping architecture for enterprise AI agents based on role-based ceilings, a task-context classifier, and policy-derived combination prohibitions, reducing ov…

The paper proposes a Semantic Gateway and a Zero-Trust security model to formally validate and secure autonomous AI agents operating in enterprise systems, achieving a 100% discovery rate of unauthori…

This paper separates three mechanisms contributing to pipeline safety in multi-agent large language models and introduces a controlled contrast design to evaluate their impact.

The paper introduces Sophrosyne, a system that moderates LLM agent exploration in relational data systems, significantly reducing over-exploration and boosting SQL generation accuracy by guiding the a…

The paper proposes Proof-Carrying Agent Actions (PCAA), a runtime-neutral governance model that uses action certificates to consistently track and authorize high-risk actions across diverse and hetero…

The paper proposes a layered, server-side isolation architecture to secure Retrieval-Augmented Generation (RAG) and agentic AI systems in multitenant enterprise environments, ensuring that retrieval a…

The paper introduces GAAP, an execution environment that deterministically guarantees the confidentiality of private user data by enforcing user-defined permission specifications on AI agents, even ag…

SecureMCP proposes a novel, policy-enforced framework that integrates Role-Based Access Control (RBAC) with an MCP server to provide multi-layer, fine-grained defense against malicious LLM-generated S…

The paper proposes an organization-scoped LLM agent runtime architecture designed to provide an auditable, model-agnostic platform for regulated cybersecurity operations, integrating deeply with exist…

The paper proposes a novel, organization-scoped LLM agent runtime architecture designed specifically for regulated cybersecurity operations, ensuring auditable context and integration with existing se…

BADGER is a unified, production-grade evaluation framework that integrates text-to-SQL assessment with agentic behavior evaluation, significantly outperforming existing benchmarks on industry queries.

This paper introduces progressive crystallization, a lifecycle for AI agents in IT operations that converts validated agent behaviors into cheaper and more reproducible deterministic workflows, increa…

The paper analyzes how runtime safety enforcement impacts the performance of multi-step LLM agents, finding that while safety mechanisms can block unsafe actions, they impose a significant performance…

The paper introduces a certified purity architecture that strengthens governance in cognitive workflow systems by replacing insufficient runtime checks with cryptographically attested structural guara…

The paper develops a unified, cross-layer security framework for autonomous LLM agents operating in agentic commerce, identifying key attack vectors and proposing a layered defense architecture.

The paper proposes the Redpanda Agentic Data Plane (ADP), an architecture that uses out-of-band metadata channels to deterministically enforce security policies and governance for autonomous AI agents…