{"total":160,"rows":[{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606,"area":null},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431,"area":null},{"id":"2306.02224","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","created":"2023-06-04","cited_by_count":255,"area":null},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195,"area":null},{"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":"2106.00737","title":"Implicit Representations of Meaning in Neural Language Models","created":"2021-06-01","cited_by_count":180,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156,"area":null},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2309.09971","title":"MindAgent: Emergent Gaming Interaction","created":"2023-09-18","cited_by_count":88,"area":null},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2510.08558","title":"Agent Learning via Early Experience","created":"2025-10-09","cited_by_count":85,"area":null},{"id":"2102.13249","title":"Chess as a Testbed for Language Model State Tracking","created":"2021-02-26","cited_by_count":72,"area":null},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2403.11322","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","created":"2024-03-17","cited_by_count":65,"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":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2308.01404","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","created":"2023-07-05","cited_by_count":47,"area":null},{"id":"2407.02511","title":"LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning","created":"2024-06-20","cited_by_count":45,"area":null},{"id":"2305.02363","title":"Entity Tracking in Language Models","created":"2023-05-03","cited_by_count":44,"area":null},{"id":"2511.03773","title":"Scaling Agent Learning via Experience Synthesis","created":"2025-11-05","cited_by_count":44,"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":"2401.16467","title":"ReGAL: Refactoring Programs to Discover Generalizable Abstractions","created":"2024-01-29","cited_by_count":36,"area":null},{"id":"2312.06853","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback","created":"2023-12-11","cited_by_count":33,"area":null},{"id":"2405.15143","title":"Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models","created":"2024-05-24","cited_by_count":33,"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":"2410.07927","title":"Efficient Reinforcement Learning with Large Language Model Priors","created":"2024-10-10","cited_by_count":30,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"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":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2104.07972","title":"Language Models are Few-Shot Butlers","created":"2021-04-16","cited_by_count":27,"area":null},{"id":"2106.00596","title":"Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks","created":"2021-06-01","cited_by_count":26,"area":null},{"id":"2406.12158","title":"LLMs Are Prone to Fallacies in Causal Inference","created":"2024-06-18","cited_by_count":23,"area":null},{"id":"2201.01251","title":"Multi-Stage Episodic Control for Strategic Exploration in Text Games","created":"2022-01-04","cited_by_count":22,"area":null},{"id":"2107.08408","title":"Pre-trained Language Models as Prior Knowledge for Playing Text-based Games","created":"2021-07-18","cited_by_count":21,"area":null},{"id":"2310.03779","title":"HandMeThat: Human-Robot Communication in Physical and Social Environments","created":"2023-10-05","cited_by_count":20,"area":null},{"id":"2103.09815","title":"TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL","created":"2021-03-17","cited_by_count":18,"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":"2403.16527","title":"Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art","created":"2024-03-25","cited_by_count":17,"area":null},{"id":"2407.12979","title":"Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models","created":"2024-07-17","cited_by_count":17,"area":null},{"id":"2502.12435","title":"A Survey on Large Language Models for Automated Planning","created":"2025-02-18","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":"2404.17027","title":"Player-Driven Emergence in LLM-Driven Game Narrative","created":"2024-04-25","cited_by_count":16,"area":null},{"id":"2405.02178","title":"Assessing and Verifying Task Utility in LLM-Powered Applications","created":"2024-05-03","cited_by_count":16,"area":null},{"id":"2503.00870","title":"NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains","created":"2025-03-02","cited_by_count":15,"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":"2104.09469","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","created":"2021-04-19","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":"2206.01134","title":"Language and Culture Internalisation for Human-Like Autotelic AI","created":"2022-06-02","cited_by_count":14,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2208.01174","title":"TextWorldExpress: Simulating Text Games at One Million Steps Per Second","created":"2022-08-01","cited_by_count":13,"area":null},{"id":"2402.12621","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2407.00401","title":"PUZZLES: A Benchmark for Neural Algorithmic Reasoning","created":"2024-06-29","cited_by_count":13,"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":"2102.09557","title":"Knowledge Hypergraph Embedding Meets Relational Algebra","created":"2021-02-18","cited_by_count":11,"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":"2402.13109","title":"CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2504.14128","title":"TALES: Text Adventure Learning Environment Suite","created":"2025-04-19","cited_by_count":11,"area":null},{"id":"2103.02363","title":"Reinforcement Learning with External Knowledge by using Logical Neural Networks","created":"2021-03-03","cited_by_count":10,"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":"2310.01459","title":"NarrativePlay: Interactive Narrative Understanding","created":"2023-10-02","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":"2206.00142","title":"IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2110.08470","title":"Case-based Reasoning for Better Generalization in Textual Reinforcement Learning","created":"2021-10-16","cited_by_count":8,"area":null},{"id":"2303.05069","title":"Conceptual Reinforcement Learning for Language-Conditioned Tasks","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2102.11387","title":"Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation","created":"2021-02-22","cited_by_count":7,"area":null},{"id":"2107.00956","title":"SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-07-02","cited_by_count":7,"area":null},{"id":"2301.10107","title":"Story Shaping: Teaching Agents Human-like Behavior with Stories","created":"2023-01-24","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2406.12000","title":"Look Further Ahead: Testing the Limits of GPT-4 in Path Planning","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2410.16710","title":"Influential Language Data Selection via Gradient Trajectory Pursuit","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2604.07774","title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","created":"2026-04-09","cited_by_count":7,"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":"2212.10012","title":"Language Modeling with Latent Situations","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2305.08876","title":"Neurosymbolic AI and its Taxonomy: a survey","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2406.16294","title":"LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2502.10177","title":"STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2503.14427","title":"VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2306.09922","title":"Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions","created":"2023-06-16","cited_by_count":5,"area":null},{"id":"2308.01734","title":"Ambient Adventures: Teaching ChatGPT on Developing Complex Stories","created":"2023-08-03","cited_by_count":5,"area":null},{"id":"2408.05861","title":"Temporal Knowledge-Graph Memory in a Partially Observable Environment","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2106.05387","title":"Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2206.08851","title":"SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments","created":"2022-06-17","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":"2310.16135","title":"Can You Follow Me? Testing Situational Understanding in ChatGPT","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2402.11489","title":"What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models","created":"2024-02-18","cited_by_count":4,"area":null},{"id":"2505.03547","title":"STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game","created":"2025-05-06","cited_by_count":4,"area":null},{"id":"2505.12439","title":"Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2203.06671","title":"Summarizing a virtual robot's past actions in natural language","created":"2022-03-13","cited_by_count":3,"area":null},{"id":"2305.04082","title":"A Minimal Approach for Natural Language Action Space in Text-based Games","created":"2023-05-06","cited_by_count":3,"area":null},{"id":"2311.07687","title":"Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games","created":"2023-11-13","cited_by_count":3,"area":null}],"next_cursor":"100"}