{"total":51,"rows":[{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"area":null},{"id":"2405.06624","title":"Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems","created":"2024-05-10","cited_by_count":96,"area":"wm"},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81,"area":"wm"},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"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":"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":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2301.02324","title":"Reasoning about Causality in Games","created":"2023-01-05","cited_by_count":20,"area":"lr"},{"id":"2606.08275","title":"Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures","created":"2026-06-06","cited_by_count":20,"area":"agents"},{"id":"2501.13011","title":"MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking","created":"2025-01-22","cited_by_count":19,"area":"alignment"},{"id":"2306.01424","title":"Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","cited_by_count":13,"area":"agents"},{"id":"2202.10816","title":"Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness","created":"2022-02-22","cited_by_count":10,"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":"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":"2505.19806","title":"Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2507.00979","title":"Enhancing LLM Agent Safety via Causal Influence Prompting","created":"2025-07-01","cited_by_count":5,"area":"agents"},{"id":"2507.17257","title":"Agent Identity Evals: Measuring Agentic Identity","created":"2025-07-23","cited_by_count":5,"area":"agents"},{"id":"2307.05059","title":"On Imperfect Recall in Multi-Agent Influence Diagrams","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2105.06268","title":"Intelligence and Unambitiousness Using Algorithmic Information Theory","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2207.02847","title":"Scoring Rules for Performative Binary Prediction","created":"2022-07-05","cited_by_count":3,"area":null},{"id":"2307.10987","title":"Characterising Decision Theories with Mechanised Causal Graphs","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2410.00258","title":"Possible Principles for Aligned Structure Learning Agents","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2506.02923","title":"The Limits of Predicting Agents from Behaviour","created":"2025-06-03","cited_by_count":3,"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":"2209.11801","title":"Solutions to preference manipulation in recommender systems require knowledge of meta-preferences","created":"2022-09-14","cited_by_count":1,"area":null},{"id":"2309.11984","title":"State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.11334","title":"Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs","created":"2023-10-17","cited_by_count":1,"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":"2503.06323","title":"Higher-Order Belief in Incomplete Information MAIDs","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2511.17953","title":"On Transportability for Structural Causal Bandits","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2606.12268","title":"The Impossibility of Eliciting Latent Knowledge","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2205.08178","title":"Active learning of causal probability trees","created":"2022-05-17","cited_by_count":0,"area":null},{"id":"2306.00636","title":"Unfair Utilities and First Steps Towards Improving Them","created":"2023-06-01","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":"2509.25715","title":"MuPlon: Multi-Path Causal Optimization for Claim Verification through Controlling Confounding","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.23545","title":"Planning under Distribution Shifts with Causal POMDPs","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.27611","title":"What Does a System Modify When It Modifies Itself?","created":"2026-03-29","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},{"id":"2605.02681","title":"The Design and Composition of Structural Causal Decision Processes","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2607.16717","title":"A Causal Markov Condition for Value","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.13456","title":"A Unifying Perspective on Causal World Models: From Observations to Representations to Structure","created":"2026-08-13","cited_by_count":0,"area":"wm"}],"next_cursor":null}