{"total":88,"rows":[{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421,"area":"agents"},{"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":"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":"2310.10134","title":"CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization","created":"2023-10-16","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":"2503.22458","title":"Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey","created":"2025-03-28","cited_by_count":57,"area":"agents"},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2410.02189","title":"Agent-Oriented Planning in Multi-Agent Systems","created":"2024-10-03","cited_by_count":36,"area":"agents"},{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35,"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":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2106.09608","title":"Learning Knowledge Graph-based World Models of Textual Environments","created":"2021-06-17","cited_by_count":31,"area":"wm"},{"id":"2305.12487","title":"Augmenting Autotelic Agents with Large Language Models","created":"2023-05-21","cited_by_count":30,"area":"agents"},{"id":"2104.07972","title":"Language Models are Few-Shot Butlers","created":"2021-04-16","cited_by_count":27,"area":null},{"id":"2404.09911","title":"ChatShop: Interactive Information Seeking with Language Agents","created":"2024-04-15","cited_by_count":24,"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":"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":"2103.13552","title":"Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents","created":"2021-03-25","cited_by_count":20,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2106.09146","title":"Contrastive Reinforcement Learning of Symbolic Reasoning Domains","created":"2021-06-16","cited_by_count":17,"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":"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":"2011.02511","title":"Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Tasks","created":"2020-11-04","cited_by_count":12,"area":"alignment"},{"id":"2211.04591","title":"Learning to Follow Instructions in Text-Based Games","created":"2022-11-08","cited_by_count":12,"area":null},{"id":"2405.13828","title":"Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations","created":"2024-05-22","cited_by_count":12,"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":"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":"2305.05091","title":"Knowledge-enhanced Agents for Interactive Text Games","created":"2023-05-08","cited_by_count":10,"area":"agents"},{"id":"2110.03262","title":"Situated Dialogue Learning through Procedural Environment Generation","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2601.07577","title":"Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents","created":"2026-01-12","cited_by_count":9,"area":"agents"},{"id":"2106.02317","title":"Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory","created":"2021-06-04","cited_by_count":8,"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":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2406.05872","title":"STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models","created":"2024-06-09","cited_by_count":8,"area":"agents"},{"id":"1905.09700","title":"Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces","created":"2019-05-23","cited_by_count":7,"area":"offlinerl"},{"id":"2106.00897","title":"Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2404.10887","title":"Grounded Language Agent for Product Search via Intelligent Web Interactions","created":"2024-04-16","cited_by_count":7,"area":"agents"},{"id":"2606.05885","title":"When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training","created":"2026-06-04","cited_by_count":7,"area":"agents"},{"id":"2606.02355","title":"SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training","created":"2026-06-01","cited_by_count":6,"area":"agents"},{"id":"2104.00527","title":"Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Two-phase Flow","created":"2021-03-31","cited_by_count":5,"area":null},{"id":"2106.01650","title":"Learning and Executing Re-usable Behaviour Trees from Natural Language Instruction","created":"2021-06-03","cited_by_count":5,"area":null},{"id":"2405.10310","title":"Stochastic Q-learning for Large Discrete Action Spaces","created":"2024-05-16","cited_by_count":5,"area":"deeprl"},{"id":"2503.14555","title":"A Generalist Hanabi Agent","created":"2025-03-17","cited_by_count":5,"area":"deeprl"},{"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":"2305.19891","title":"Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces","created":"2023-05-31","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":"2401.07553","title":"Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2404.18978","title":"Towards Generalizable Agents in Text-Based Educational Environments: A Study of Integrating RL with LLMs","created":"2024-04-29","cited_by_count":4,"area":"agents"},{"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":"2510.24891","title":"Idea2Plan: Exploring AI-Powered Research Planning","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2201.07224","title":"NSGZero: Efficiently Learning Non-Exploitable Policy in Large-Scale Network Security Games with Neural Monte Carlo Tree Search","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2204.13971","title":"Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach","created":"2022-04-29","cited_by_count":3,"area":null},{"id":"2302.05507","title":"Language Decision Transformers with Exponential Tilt for Interactive Text Environments","created":"2023-02-10","cited_by_count":3,"area":"offlinerl"},{"id":"2309.11564","title":"Hierarchical reinforcement learning with natural language subgoals","created":"2023-09-20","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},{"id":"2312.07368","title":"Sequential Planning in Large Partially Observable Environments guided by LLMs","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2410.09252","title":"DAVIS: Planning Agent with Knowledge Graph-Powered Inner Monologue","created":"2024-10-11","cited_by_count":3,"area":"rag"},{"id":"2410.21151","title":"BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces","created":"2024-10-28","cited_by_count":3,"area":"offlinerl"},{"id":"2606.24893","title":"AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2201.12126","title":"Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods","created":"2022-01-28","cited_by_count":2,"area":null},{"id":"2210.08384","title":"Revisiting the Roles of \"Text\" in Text Games","created":"2022-10-15","cited_by_count":2,"area":null},{"id":"2302.10720","title":"Learning to Play Text-based Adventure Games with Maximum Entropy Reinforcement Learning","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2304.07258","title":"Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games","created":"2023-04-14","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":"2411.02223","title":"Positive Experience Reflection for Agents in Interactive Text Environments","created":"2024-11-04","cited_by_count":2,"area":"agents"},{"id":"2509.24116","title":"Dual-Scale World Models for LLM Agents Towards Hard-Exploration Problems","created":"2025-09-28","cited_by_count":2,"area":"wm"},{"id":"2302.11917","title":"Diverse Policy Optimization for Structured Action Space","created":"2023-02-23","cited_by_count":1,"area":"alignment"},{"id":"2310.10250","title":"Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2405.06499","title":"Aspect-based Sentiment Evaluation of Chess Moves (ASSESS): an NLP-based Method for Evaluating Chess Strategies from Textbooks","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2411.08432","title":"One STEP at a time: Language Agents are Stepwise Planners","created":"2024-11-13","cited_by_count":1,"area":"agents"},{"id":"2504.06868","title":"Persona Dynamics: Unveiling the Impact of Personality Traits on Agents in Text-Based Games","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2505.16311","title":"Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2207.00468","title":"Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings","created":"2022-07-01","cited_by_count":0,"area":null},{"id":"2211.06014","title":"Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2302.05244","title":"A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorld","created":"2023-02-10","cited_by_count":0,"area":null},{"id":"2311.01468","title":"Remember what you did so you know what to do next","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2402.11653","title":"Combinatorial Client-Master Multiagent Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing","created":"2024-02-18","cited_by_count":0,"area":null},{"id":"2404.10174","title":"On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2408.12121","title":"Emotion-Agent: Unsupervised Deep Reinforcement Learning with Distribution-Prototype Reward for Continuous Emotional EEG Analysis","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2502.17538","title":"Policy Learning with a Natural Language Action Space: A Causal Approach","created":"2025-02-24","cited_by_count":0,"area":"alignment"},{"id":"2505.12109","title":"SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces","created":"2025-05-17","cited_by_count":0,"area":"deeprl"},{"id":"2602.22452","title":"CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines","created":"2026-02-25","cited_by_count":0,"area":"wm"},{"id":"2605.12379","title":"Discrete Flow Matching for Offline-to-Online Reinforcement Learning","created":"2026-05-12","cited_by_count":0,"area":"diffusion"},{"id":"2608.23055","title":"Macro-Action Topological Navigation under Noisy Localization using Reinforcement Learning","created":"2026-08-24","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}