{"total":25,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2112.15422","title":"Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)","created":"2021-11-25","cited_by_count":55,"area":null},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2504.21848","title":"Characterizing AI Agents for Alignment and Governance","created":"2025-04-30","cited_by_count":30,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2609.04170","title":"A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms","created":"2026-09-03","cited_by_count":5,"area":null},{"id":"2112.00940","title":"Reward-Free Attacks in Multi-Agent Reinforcement Learning","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2206.11812","title":"Formalizing the Problem of Side Effect Regularization","created":"2022-06-23","cited_by_count":3,"area":null},{"id":"2605.16198","title":"Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems","created":"2026-05-15","cited_by_count":3,"area":null},{"id":"2305.04692","title":"Anticipatory Planning: Improving Long-Lived Planning by Estimating Expected Cost of Future Tasks","created":"2023-05-08","cited_by_count":2,"area":null},{"id":"2106.02617","title":"Be Considerate: Objectives, Side Effects, and Deciding How to Act","created":"2021-06-04","cited_by_count":1,"area":null},{"id":"2510.08624","title":"Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2511.04177","title":"When Assisting One Disempowers Another","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2101.12509","title":"Challenges for Using Impact Regularizers to Avoid Negative Side Effects","created":"2021-01-29","cited_by_count":0,"area":null},{"id":"2112.10190","title":"Demanding and Designing Aligned Cognitive Architectures","created":"2021-12-19","cited_by_count":0,"area":null},{"id":"2303.03139","title":"Low impact agency: review and discussion","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2304.03081","title":"Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2510.04901","title":"Focused Skill Discovery: Learning to Control Specific State Variables while Minimizing Side Effects","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2603.06816","title":"\"Dark Triad\" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.21155","title":"Multi-Agent Empowerment and Emergence of Complex Behavior in Groups","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.24527","title":"Interoceptive machine framework: Toward interoception-inspired regulatory architectures in artificial intelligence","created":"2026-04-27","cited_by_count":0,"area":null}],"next_cursor":null}