English
Related papers

Related papers: Foundations of a Time-Consistent Counterfactual Ac…

200 papers

We present a methodology for estimating collision risk from counterfactual simulated scenarios built on sensor data from automated driving systems (ADS) or naturalistic driving databases. Two-agent conflicts are assessed by detecting and…

Robotics · Computer Science 2025-06-10 Sreeja Roy-Singh , Sarvesh Kolekar , Daniel P. Bonny , Kyle Foss

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…

Artificial Intelligence · Computer Science 2026-03-04 Varun Pratap Bhardwaj

Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such…

Artificial Intelligence · Computer Science 2026-04-28 Rong Xiang

Generative and agentic artificial intelligence is entering financial markets faster than existing governance can adapt. Current model-risk frameworks assume static, well-specified algorithms and one-time validations; large language models…

Computers and Society · Computer Science 2025-12-16 Eren Kurshan , Tucker Balch , David Byrd

The rapid deployment of autonomous AI agents across enterprise, healthcare, and safety-critical environments has created a fundamental governance gap. Existing approaches, runtime guardrails, training-time alignment, and post-hoc auditing…

Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any code change. We propose the \textbf{Informational Viability Principle}: governing an…

Artificial Intelligence · Computer Science 2026-04-28 German Marin , Jatin Chaudhary

An agentic-AI runtime issues tool calls, sends messages, and actuates devices on behalf of an LLM. Catching the four ways an action can diverge from its audit record -- F1 gate-bypass, F2 audit-forgery, silent host failure, F4 wrong-target,…

Cryptography and Security · Computer Science 2026-05-05 Alfredo Metere

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,…

Artificial Intelligence · Computer Science 2026-05-15 Drewry H. Morris , Luis Valles , Reza Hosseini Ghomi

Populating our world with hyperintelligent machines obliges us to examine cognitive behaviors observed across domains that suggest autonomy may be a fundamental property of cognitive systems, and while not inherently adversarial, it…

Neurons and Cognition · Quantitative Biology 2025-06-09 Andrea Morris

This paper describes the development of a counterfactual Root Cause Analysis diagnosis approach for an industrial multivariate time series environment. It drives the attention toward the Point of Incipient Failure, which is the moment in…

Machine Learning · Computer Science 2024-07-17 Alexandre Trilla , Rajesh Rajendran , Ossee Yiboe , Quentin Possamaï , Nenad Mijatovic , Jordi Vitrià

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…

Cryptography and Security · Computer Science 2026-03-16 Aojie Yuan , Zhiyuan Su , Yue Zhao

We formalize Prescriptive Artificial Intelligence as a distinct paradigm for human-AI decision collaboration in high-stakes environments. Unlike predictive systems optimized for outcome accuracy, prescriptive systems are designed to…

Artificial Intelligence · Computer Science 2026-03-26 Pedro Passos , Patrick Moratori

The boundary of the firm is determined by coordination cost. We argue that agentic AI induces a structural change in how coordination costs scale: in prior modular systems, integration cost grew with interaction topology (O(n^2) in the…

Computer Science and Game Theory · Computer Science 2026-02-26 Tassilo Klein , Sebastian Wieczorek

When AI systems make errors in high-stakes domains like medical diagnosis or autonomous vehicles, a single algorithmic flaw across varying operational contexts can generate highly heterogeneous losses that challenge traditional insurance…

Machine Learning · Computer Science 2026-03-31 Dimitris Bertsimas , Agni Orfanoudaki

Significant digitalization of financial services in a short period of time has led to an urgent demand to have autonomous, transparent and real-time credit risk decision making systems. The traditional machine learning models are effective…

Artificial Intelligence · Computer Science 2026-01-06 Chandra Sekhar Kubam

The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing…

Artificial Intelligence · Computer Science 2026-03-17 Florin Adrian Chitan

Counterfactual explanations provide human-understandable reasoning for AI-made decisions by describing minimal changes to input features that would alter a model's prediction. To be truly useful in practice, such explanations must be…

Machine Learning · Computer Science 2025-08-15 Asiful Arefeen , Shovito Barua Soumma , Hassan Ghasemzadeh

Recently, eXplainable AI (XAI) research has focused on counterfactual explanations as post-hoc justifications for AI-system decisions (e.g. a customer refused a loan might be told: If you asked for a loan with a shorter term, it would have…

Artificial Intelligence · Computer Science 2023-05-10 Saugat Aryal , Mark T Keane

Modern cloud and enterprise systems rely on identity-centric authorization, assuming that callers possessing valid credentials are safe to execute commands. The emergence of autonomous AI agents invalidates this assumption: agents can…

Artificial Intelligence · Computer Science 2026-05-18 Jun He , Deying Yu

This position paper argues that AI-assisted software engineering requires explicit mechanisms for tracking the epistemic status and temporal validity of architectural decisions. LLM coding assistants generate decisions faster than teams can…

Software Engineering · Computer Science 2026-01-30 Sankalp Gilda , Shlok Gilda