{"total":13,"rows":[{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28,"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":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2205.04279","title":"Aligned with Whom? Direct and social goals for AI systems","created":"2022-05-09","cited_by_count":7,"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":"2112.13523","title":"Interpreting Dynamical Systems as Bayesian Reasoners","created":"2021-12-27","cited_by_count":5,"area":null},{"id":"2508.13247","title":"Goal-Directedness is in the Eye of the Beholder","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2605.00248","title":"Causal Foundations of Collective Agency","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2609.15407","title":"Can AI systems have free will?","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}