{"total":37,"rows":[{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2306.00924","title":"Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker","created":"2023-06-01","cited_by_count":95,"area":null},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57,"area":null},{"id":"2406.06485","title":"Can Language Models Serve as Text-Based World Simulators?","created":"2024-06-10","cited_by_count":52,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"2110.10963","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","created":"2021-10-21","cited_by_count":30,"area":null},{"id":"2305.11598","title":"Introspective Tips: Large Language Model for In-Context Decision Making","created":"2023-05-19","cited_by_count":28,"area":null},{"id":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2101.10244","title":"Process-Level Representation of Scientific Protocols with Interactive Annotation","created":"2021-01-25","cited_by_count":16,"area":null},{"id":"2112.08907","title":"Inherently Explainable Reinforcement Learning in Natural Language","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2103.07011","title":"Towards Socially Intelligent Agents with Mental State Transition and Human Utility","created":"2021-03-12","cited_by_count":14,"area":null},{"id":"2109.09478","title":"A Survey of Text Games for Reinforcement Learning informed by Natural Language","created":"2021-09-20","cited_by_count":14,"area":null},{"id":"2211.04591","title":"Learning to Follow Instructions in Text-Based Games","created":"2022-11-08","cited_by_count":12,"area":null},{"id":"2108.01928","title":"How to Query Language Models?","created":"2021-08-04","cited_by_count":11,"area":null},{"id":"2109.09968","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","created":"2021-09-21","cited_by_count":11,"area":null},{"id":"2211.00247","title":"Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning","created":"2022-11-01","cited_by_count":11,"area":null},{"id":"2204.09597","title":"Perceiving the World: Question-guided Reinforcement Learning for Text-based Games","created":"2022-03-20","cited_by_count":10,"area":null},{"id":"2205.06111","title":"Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2210.07382","title":"Behavior Cloned Transformers are Neurosymbolic Reasoners","created":"2022-10-13","cited_by_count":10,"area":null},{"id":"2110.03262","title":"Situated Dialogue Learning through Procedural Environment Generation","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2110.10973","title":"LOA: Logical Optimal Actions for Text-based Interaction Games","created":"2021-10-21","cited_by_count":6,"area":null},{"id":"2510.21131","title":"Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2201.02734","title":"Building Human-like Communicative Intelligence: A Grounded Perspective","created":"2022-01-02","cited_by_count":4,"area":null},{"id":"2307.02689","title":"Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2403.10692","title":"EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning","created":"2024-03-15","cited_by_count":3,"area":null},{"id":"2109.00077","title":"Interactive Machine Comprehension with Dynamic Knowledge Graphs","created":"2021-08-31","cited_by_count":2,"area":null},{"id":"2307.03906","title":"ScriptWorld: Text Based Environment For Learning Procedural Knowledge","created":"2023-07-08","cited_by_count":2,"area":null},{"id":"2201.08520","title":"Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2209.04105","title":"An Analysis of Deep Reinforcement Learning Agents for Text-based Games","created":"2022-09-09","cited_by_count":1,"area":null},{"id":"2307.12179","title":"Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs","created":"2023-07-22","cited_by_count":1,"area":null},{"id":"2311.01928","title":"Constructing Temporal Dynamic Knowledge Graphs from Interactive Text-based Games","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2509.00740","title":"Efficient Graph Understanding with LLMs via Structured Context Injection","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2604.11611","title":"Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2211.16002","title":"DiffG-RL: Leveraging Difference between State and Common Sense","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2411.01807","title":"Can Language Models Enable In-Context Database?","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2602.04557","title":"Textual Planning with Explicit Latent Transitions","created":"2026-02-04","cited_by_count":0,"area":null}],"next_cursor":null}