{"total":51,"rows":[{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2102.01685","title":"Agent Incentives: A Causal Perspective","created":"2021-02-02","cited_by_count":51,"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":"2405.01576","title":"Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2204.12993","title":"Counterfactual harm","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28,"area":null},{"id":"2109.04083","title":"User Tampering in Reinforcement Learning Recommender Systems","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2307.01452","title":"Causal Reinforcement Learning: A Survey","created":"2023-07-04","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":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2102.05008","title":"Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice","created":"2021-02-09","cited_by_count":9,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2507.07484","title":"Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models","created":"2025-07-10","cited_by_count":7,"area":null},{"id":"2508.04632","title":"IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2308.15605","title":"Benchmarks for Detecting Measurement Tampering","created":"2023-08-29","cited_by_count":6,"area":null},{"id":"2202.11629","title":"A Complete Criterion for Value of Information in Soluble Influence Diagrams","created":"2022-02-23","cited_by_count":5,"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":"2106.05402","title":"Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective","created":"2021-06-09","cited_by_count":4,"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":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2102.00834","title":"Counterfactual Planning in AGI Systems","created":"2021-01-29","cited_by_count":2,"area":null},{"id":"2301.07416","title":"Learning to Participate through Trading of Reward Shares","created":"2023-01-18","cited_by_count":2,"area":null},{"id":"2602.05656","title":"Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2605.01643","title":"AI Alignment via Incentives and Correction","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2503.06323","title":"Higher-Order Belief in Incomplete Information MAIDs","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2602.01699","title":"Mitigating loss of control in advanced AI systems through instrumental goal trajectories","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2604.13609","title":"Golden Handcuffs make safer AI agents","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.19845","title":"Deconstructing Superintelligence: Identity, Self-Modification and Diff\\'erance","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2604.28056","title":"RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2606.23597","title":"Against Proxy Optimization","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2609.39102","title":"False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2112.10190","title":"Demanding and Designing Aligned Cognitive Architectures","created":"2021-12-19","cited_by_count":0,"area":null},{"id":"2203.10629","title":"Explicit User Manipulation in Reinforcement Learning Based Recommender Systems","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2207.08040","title":"Reinforcement Learning For Survival, A Clinically Motivated Method For Critically Ill Patients","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2402.09734","title":"Agents Need Not Know Their Purpose","created":"2024-02-15","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":"2503.17674","title":"MultiScale Contextual Bandits for Long Term Objectives","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2509.02391","title":"Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor It","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.25471","title":"An Aristotelian ontology of instrumental goals: Structural features to be managed and not failures to be eliminated","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2605.02175","title":"Intervention Complexity as a Canonical Reward and a Measure of Intelligence","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.02681","title":"The Design and Composition of Structural Causal Decision Processes","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.16914","title":"Greed Is Learned: Visible Incentives as Reward-Hacking Triggers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.06012","title":"HERALD: Counterfactual Audits and Minimal Repairs for Proof-of-Retrieval Rewards","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.35591","title":"Language Models Act on Hidden Valence","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16500","title":"Self-Verifier Capture in Unified Visual Generators: Diagnosing and Repairing Closed-Loop Self-Reward","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}