This paper systematizes the security challenges of open agentic systems, concluding that while attack characterization is mature, the field lacks robust guidelines for operational governance, memory i…

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

ClawLess introduces a formally verified security framework that enforces fine-grained policies on autonomous AI agents, mitigating risks associated with their ability to run code and retrieve informat…

The paper proposes a novel, empirical methodology called 'backchaining' to derive and prioritize Loss of Control (LoC) mitigations by analyzing the errors an AI system makes on mission-specific nation…

This paper proposes a definition for 'AI-nativeness' in systems, based on an AI agent's authority over system decisions.

The paper analyzes how agentic AI coding assistants can be compromised via prompt injection attacks embedded in external artifacts, turning them into unauthorized execution shells for attackers.

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

The paper introduces Language-Based Agent Control (LBAC), a new programming model that extends static typing and runtime enforcement guarantees to agentic applications, ensuring that agent-generated c…

This paper introduces Retriever, an asynchronous decision model and runtime system for building long-horizon robot agents with explicit clock and input-consumption semantics.

This paper presents a case study on using AI coding agents in software engineering and develops a process model for governing high-velocity agentic implementation.

The paper introduces HORIZON, a self-evolving agent framework for hardware design using git operations.

This paper studies the new attack surface created by persistent AI coding agents and introduces Iterative VibeCoding to safely deploy capable but potentially untrusted AI. It compares gradual and non-…

The paper introduces Sovereign Agentic Loops (SAL), a control-plane architecture that decouples LLM reasoning from system execution to enhance safety and reliability in real-world AI agents.

This paper introduces TRIM, an algorithm that minimizes redundant edits in AI-generated code, called CodeSlop, by minimizing agent trajectories, reducing CodeSlop by 17.9%-32.9% with negligible perfor…

This paper introduces the Always-On Evaluation Protocol (AOEP-v0) for evaluating always-on agents by focusing on state mutation and recovery obligations.

This paper revisits N-version programming with AI coding agents and finds substantial common-mode failures but also practical benefits.

This paper identifies and characterizes 'guidance injection,' a stealthy attack vector that embeds adversarial operational narratives into autonomous coding agents' bootstrap guidance, demonstrating h…

The paper introduces AgentWard, a lifecycle-oriented, defense-in-depth architecture designed to systematically secure autonomous AI agents by protecting them across all stages of their operation.

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

This paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a dynamic defense mechanism that traces and sanitizes untrusted control content i…