{"total":15,"rows":[{"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":"2410.18819","title":"From Imitation to Introspection: Probing Self-Consciousness in Language Models","created":"2024-10-24","cited_by_count":14,"area":null},{"id":"2305.19223","title":"Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety","created":"2023-05-30","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":"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":"2602.00190","title":"From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models","created":"2026-01-30","cited_by_count":2,"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":"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":"2504.13210","title":"Graphical Models for Decision-Making: Integrating Causality and Game Theory","created":"2025-04-16","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":"2607.09954","title":"A Knowledge-Based Multi-Agent Framework for Security Control Recommendation","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.19531","title":"Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent States","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.05459","title":"Compiling VGDL into Causal Models","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}