{"total":36,"rows":[{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2109.06835","title":"The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation","created":"2021-09-14","cited_by_count":97,"area":null},{"id":"2202.13330","title":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","created":"2022-02-27","cited_by_count":63,"area":null},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30,"area":null},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2203.10759","title":"A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots","created":"2022-03-21","cited_by_count":13,"area":null},{"id":"2205.05589","title":"KETOD: Knowledge-Enriched Task-Oriented Dialogue","created":"2022-05-11","cited_by_count":12,"area":null},{"id":"2105.08301","title":"Wizard of Search Engine: Access to Information Through Conversations with Search Engines","created":"2021-05-18","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":"2112.02862","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2502.09642","title":"Krutrim LLM: Multilingual Foundational Model for over a Billion People","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2201.06849","title":"Toward Self-learning End-to-End Task-Oriented Dialog Systems","created":"2022-01-18","cited_by_count":9,"area":null},{"id":"2110.06905","title":"Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue","created":"2021-10-13","cited_by_count":6,"area":null},{"id":"2605.07847","title":"Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2110.02148","title":"NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback","created":"2021-10-05","cited_by_count":5,"area":null},{"id":"2111.01398","title":"Integrating Pretrained Language Model for Dialogue Policy Learning","created":"2021-11-02","cited_by_count":5,"area":null},{"id":"2407.08067","title":"On LLM Wizards: Identifying Large Language Models' Behaviors for Wizard of Oz Experiments","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2407.21693","title":"TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities","created":"2024-07-31","cited_by_count":4,"area":null},{"id":"2110.11514","title":"SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching","created":"2021-10-21","cited_by_count":3,"area":null},{"id":"2108.01487","title":"WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue","created":"2021-08-01","cited_by_count":2,"area":null},{"id":"2311.04921","title":"Successor Features for Efficient Multisubject Controlled Text Generation","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2106.04835","title":"Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2209.02066","title":"Trust in Language Grounding: a new AI challenge for human-robot teams","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2310.18354","title":"A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2204.09719","title":"Recent Progress in Conversational AI","created":"2022-04-08","cited_by_count":0,"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":"2212.14117","title":"Improving a sequence-to-sequence nlp model using a reinforcement learning policy algorithm","created":"2022-12-28","cited_by_count":0,"area":null},{"id":"2307.06721","title":"Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative","created":"2023-07-13","cited_by_count":0,"area":null},{"id":"2309.00230","title":"JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning","created":"2023-09-01","cited_by_count":0,"area":null},{"id":"2309.02240","title":"Dialog Action-Aware Transformer for Dialog Policy Learning","created":"2023-09-05","cited_by_count":0,"area":null},{"id":"2410.22767","title":"Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2509.19695","title":"DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systems","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2604.03924","title":"Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2609.07152","title":"An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestration","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}