Related papers: Agent Behavioral Contracts: Formal Specification a…
Autonomous AI agents are deployed at unprecedented scale, yet no principled methodology exists for verifying that an agent has not regressed after changes to its prompts, tools, models, or orchestration logic. We present AgentAssay, the…
GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…
Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete environment specifications, and brittle evaluation logic that human…
The current advancement in and deployment of agentic AI systems has created a set of key challenges for the legal frameworks that govern their use. We cover two central components: first, the regulatory classification of agents under the EU…
As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…
The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…
Agentic AI systems increasingly act through tools, sub-agents, and external services, but governance controls are still commonly attached to prompts, dashboards, or post-hoc documentation. This creates a structural mismatch in regulated…
With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate…
The transition from neural machine translation to agentic workflows has revolutionized Automated Program Repair (APR). However, existing agents, despite their advanced reasoning capabilities, frequently suffer from the ``Intent Gap'' -- the…
Growing concerns over negligent or malicious uses of AI have increased the appetite for tools that help manage the risks of the technology. In 2018, licenses with behaviorial-use clauses (commonly referred to as Responsible AI Licenses)…
Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…
AI agents are AI systems that can achieve complex goals autonomously. Assessing the level of agent autonomy is crucial for understanding both their potential benefits and risks. Current assessments of autonomy often focus on specific risks…
Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve into autonomous agents deployed in open environments and increasingly connected to…
Verifying LLM-generated systems code is hard: bugs are prevalent, formal specifications are missing, and safety contracts are encoded implicitly at call sites rather than enforced at function boundaries. We propose agentic model checking, a…
Security policy enforcement in contemporary agentic systems predominantly consists of embedding natural-language policies within an agent's system prompt and delegating compliance to the agent's reasoning. This approach admits no formal…
The rapid expansion of AI-driven applications powered by large language models has led to a surge in AI interaction data, raising urgent challenges in security, accountability, and risk traceability. This paper presents AiAuditTrack (AAT),…
Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgent across two workflow paradigms and eighteen astrophysical…
Advanced reasoning models with agentic capabilities (AI agents) are deployed to interact with humans and to solve sequential decision-making problems under (approximate) utility functions and internal models. When such problems have…
Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an…
Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure,…