{"total":310,"rows":[{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276,"area":"agents"},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"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":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327,"area":"lr"},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297,"area":"agents"},{"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":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177,"area":"lr"},{"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":"2305.17390","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","created":"2023-05-27","cited_by_count":168,"area":"lr"},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156,"area":null},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"area":"lr"},{"id":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125,"area":"agents"},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"area":"lr"},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"id":"2407.04363","title":"AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents","created":"2024-07-05","cited_by_count":102,"area":"wm"},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100,"area":"offlinerl"},{"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":"2402.03610","title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents","created":"2024-02-06","cited_by_count":80,"area":"mllm"},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"area":"agents"},{"id":"2310.05746","title":"Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena","created":"2023-10-09","cited_by_count":78,"area":"lr"},{"id":"1812.04155","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","created":"2018-12-10","cited_by_count":77,"area":"offlinerl"},{"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":"2311.16714","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","created":"2023-11-28","cited_by_count":65,"area":"agents"},{"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":"2508.09124","title":"OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows","created":"2025-08-12","cited_by_count":57,"area":"agents"},{"id":"2604.05333","title":"Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills","created":"2026-04-07","cited_by_count":55,"area":"agents"},{"id":"2602.22769","title":"AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications","created":"2026-02-26","cited_by_count":53,"area":"agents"},{"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":"2310.03249","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","created":"2023-10-05","cited_by_count":49,"area":"lr"},{"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":"2512.18832","title":"From Word to World: Can Large Language Models be Implicit Text-based World Models?","created":"2025-12-21","cited_by_count":42,"area":"wm"},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2312.03815","title":"LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem","created":"2023-12-06","cited_by_count":38,"area":"agents"},{"id":"2310.03965","title":"Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models","created":"2023-10-06","cited_by_count":37,"area":"lr"},{"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":"2305.02412","title":"Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents","created":"2023-05-03","cited_by_count":32,"area":"agents"},{"id":"2110.10963","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","created":"2021-10-21","cited_by_count":30,"area":null},{"id":"2305.12487","title":"Augmenting Autotelic Agents with Large Language Models","created":"2023-05-21","cited_by_count":30,"area":"agents"},{"id":"2312.00746","title":"Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games","created":"2023-12-01","cited_by_count":30,"area":"agents"},{"id":"2410.07927","title":"Efficient Reinforcement Learning with Large Language Model Priors","created":"2024-10-10","cited_by_count":30,"area":null},{"id":"2503.07832","title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","created":"2025-03-10","cited_by_count":30,"area":"lr"},{"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":"2310.08740","title":"A Zero-Shot Language Agent for Computer Control with Structured Reflection","created":"2023-10-12","cited_by_count":28,"area":"agents"},{"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":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"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":"2406.08689","title":"Security of AI Agents","created":"2024-06-12","cited_by_count":26,"area":"agents"},{"id":"2312.17653","title":"LARP: Language-Agent Role Play for Open-World Games","created":"2023-12-24","cited_by_count":24,"area":"agents"},{"id":"2602.02488","title":"RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System","created":"2026-02-02","cited_by_count":24,"area":"agents"},{"id":"2305.14879","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","created":"2023-05-24","cited_by_count":23,"area":"wm"},{"id":"2406.12158","title":"LLMs Are Prone to Fallacies in Causal Inference","created":"2024-06-18","cited_by_count":23,"area":null},{"id":"2410.02810","title":"StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking","created":"2024-09-21","cited_by_count":23,"area":"agents"},{"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":"2408.10455","title":"IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction","created":"2024-08-19","cited_by_count":22,"area":"agents"},{"id":"2504.16855","title":"Monte Carlo Planning with Large Language Model for Text-Based Game Agents","created":"2025-04-23","cited_by_count":22,"area":"agents"},{"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":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2602.23008","title":"Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization","created":"2026-02-26","cited_by_count":19,"area":"agents"},{"id":"2605.06078","title":"Milestone-Guided Policy Learning for Long-Horizon Language Agents","created":"2026-05-07","cited_by_count":19,"area":"agents"},{"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":"2509.17325","title":"Generalizable End-to-End Tool-Use RL with Synthetic CodeGym","created":"2025-09-22","cited_by_count":17,"area":"agents"},{"id":"2510.01132","title":"A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning","created":"2025-10-01","cited_by_count":17,"area":"agents"},{"id":"2607.05804","title":"TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training","created":"2026-07-07","cited_by_count":17,"area":"distill"},{"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":"2411.00927","title":"ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents","created":"2024-11-01","cited_by_count":15,"area":"wm"},{"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}],"next_cursor":"100"}