English
Related papers

Related papers: Value Alignment Verification

200 papers

We present a rigorous, human-in-the-loop evaluation framework for assessing the performance of AI agents on the task of Air Traffic Control, grounded in a regulator-certified simulator-based curriculum used for training and testing…

Human-Computer Interaction · Computer Science 2026-01-13 Ben Carvell , Marc Thomas , Andrew Pace , Christopher Dorney , George De Ath , Richard Everson , Nick Pepper , Adam Keane , Samuel Tomlinson , Richard Cannon

One of today's most significant societal challenges is building AI systems whose behaviour, or the behaviour it enables within communities of interacting agents (human and artificial), aligns with human values. To address this challenge, we…

Artificial Intelligence · Computer Science 2026-02-09 Nardine Osman , Mark d'Inverno

One of the main research areas in Artificial Intelligence is the coding of agents (programs) which are able to learn by themselves in any situation. This means that agents must be useful for purposes other than those they were created for,…

Artificial Intelligence · Computer Science 2011-02-04 Javier Insa-Cabrera , Jose Hernandez-Orallo

This paper addresses the question of how to align AI systems with human values and situates it within a wider body of thought regarding technology and value. Far from existing in a vacuum, there has long been an interest in the ability of…

Computers and Society · Computer Science 2021-01-19 Iason Gabriel , Vafa Ghazavi

In autonomous navigation, a planning system reasons about other agents to plan a safe and plausible trajectory. Before planning starts, agents are typically processed with computationally intensive models for recognition, tracking, motion…

Robotics · Computer Science 2019-09-20 Khaled S. Refaat , Kai Ding , Natalia Ponomareva , Stéphane Ross

A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to…

Artificial Intelligence · Computer Science 2026-05-18 Aleksandr Bowkis , Marie Davidsen Buhl , Jacob Pfau , Geoffrey Irving

A definition of intelligence is given in terms of performance that can be quantitatively measured. In this study, we have presented a conceptual model of Intelligent Agent System for Automatic Vehicle Checking Agent (VCA). To achieve this…

Artificial Intelligence · Computer Science 2011-12-06 Bashir Ahmad , Shakeel Ahmad , Shahid Hussain , Muhammad Zaheer Aslam , Zafar Abbas

When autonomous vehicles encounter untrained scenarios, ensuring safety hinges on effective safety verification to prevent accidents stemming from unexpected model decisions. Reachability analysis, a method of safety verification, offers…

Systems and Control · Electrical Eng. & Systems 2025-12-05 Lingxiang Fan , Linxuan He , Haoyuan Ji , Shuo Feng

We consider the problem of designing agents able to compute optimal decisions by composing data from multiple sources to tackle tasks involving: (i) tracking a desired behavior while minimizing an agent-specific cost; (ii) satisfying safety…

Optimization and Control · Mathematics 2023-05-23 Emiland Garrabe , Martina Lamberti , Giovanni Russo

Current validation methods often rely on recorded data and basic functional checks, which may not be sufficient to encompass the scenarios an autonomous vehicle might encounter. In addition, there is a growing need for complex scenarios…

Robotics · Computer Science 2024-02-08 Marc Kaufeld , Rainer Trauth , Johannes Betz

Automated Vehicles (AVs) are rapidly maturing in the transportation domain. However, the complexity of the AV design problem is such that no single technique is sufficient to provide adequate validation of key properties such as safety,…

Software Engineering · Computer Science 2022-08-11 Maike Schwammberger , Christopher Harper , Gleifer Vaz Alves , Greg Chance , Tony Pipe , Kerstin Eder

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

Machine Learning · Computer Science 2025-07-11 Ram Potham

Multi-Agent Systems (MAS) are notoriously complex and hard to verify. In fact, it is not trivial to model a MAS, and even when a model is built, it is not always possible to verify, in a formal way, that it is actually behaving as we…

Logic in Computer Science · Computer Science 2023-06-19 Angelo Ferrando , Vadim Malvone

Agent-based models, particularly those applied to financial markets, demonstrate the ability to produce realistic, simulated system dynamics, comparable to those observed in empirical investigations. Despite this, they remain fairly…

Computational Finance · Quantitative Finance 2017-03-24 Donovan Platt , Tim Gebbie

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…

Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is…

Machine Learning · Computer Science 2024-01-18 Sunayana Rane , Polyphony J. Bruna , Ilia Sucholutsky , Christopher Kello , Thomas L. Griffiths

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…

Computation and Language · Computer Science 2025-02-27 Hao Peng , Yunjia Qi , Xiaozhi Wang , Zijun Yao , Bin Xu , Lei Hou , Juanzi Li

As increasingly capable agents are deployed, a central safety challenge is how to retain meaningful human control without modifying the underlying system. We study a minimal control interface in which an agent chooses whether to act…

Artificial Intelligence · Computer Science 2026-02-23 William Overman , Mohsen Bayati

An open problem for autonomous driving is how to validate the safety of an autonomous vehicle in simulation. Automated testing procedures can find failures of an autonomous system but these failures may be difficult to interpret due to…

Robotics · Computer Science 2020-06-29 Anthony Corso , Mykel J. Kochenderfer

Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can…

Artificial Intelligence · Computer Science 2025-10-31 Rishub Jain , Sophie Bridgers , Lili Janzer , Rory Greig , Tian Huey Teh , Vladimir Mikulik