{"total":19,"rows":[{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"area":null},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2501.09674","title":"Authenticated Delegation and Authorized AI Agents","created":"2025-01-16","cited_by_count":65,"area":null},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2406.14302","title":"Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning","created":"2024-06-20","cited_by_count":16,"area":null},{"id":"2504.11844","title":"Evaluating the Goal-Directedness of Large Language Models","created":"2025-04-16","cited_by_count":16,"area":null},{"id":"2509.08494","title":"HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2209.01619","title":"Interpreting systems as solving POMDPs: a step towards a formal understanding of agency","created":"2022-09-04","cited_by_count":7,"area":null},{"id":"2410.04683","title":"Towards Measuring Goal-Directedness in AI Systems","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2307.05059","title":"On Imperfect Recall in Multi-Agent Influence Diagrams","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2307.10987","title":"Characterising Decision Theories with Mechanised Causal Graphs","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2510.17697","title":"A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2405.16588","title":"Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games","created":"2024-05-26","cited_by_count":1,"area":null},{"id":"2412.02579","title":"Factored space models: Towards causality between levels of abstraction","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2306.14816","title":"Experiments with Detecting and Mitigating AI Deception","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2406.09318","title":"Characterising Interventions in Causal Games","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2408.12250","title":"Can Artificial Intelligence Embody Moral Values?","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2605.00248","title":"Causal Foundations of Collective Agency","created":"2026-04-30","cited_by_count":0,"area":null}],"next_cursor":null}