{"list":"other","total":101,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"id":"1603.08023","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","created":"2016-03-25","cited_by_count":356},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302},{"id":"2106.01144","title":"Towards Emotional Support Dialog Systems","created":"2021-06-02","cited_by_count":299},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279},{"id":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2305.11554","title":"ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings","created":"2023-05-19","cited_by_count":240},{"id":"2405.17935","title":"Tool Learning with Large Language Models: A Survey","created":"2024-05-28","cited_by_count":223},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2205.12255","title":"TALM: Tool Augmented Language Models","created":"2022-05-24","cited_by_count":197},{"id":"2303.09014","title":"ART: Automatic multi-step reasoning and tool-use for large language models","created":"2023-03-16","cited_by_count":197},{"id":"2403.02502","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","created":"2024-03-04","cited_by_count":197},{"id":"1711.01731","title":"A Survey on Dialogue Systems: Recent Advances and New Frontiers","created":"2017-11-06","cited_by_count":162},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2010.02795","title":"COSMIC: COmmonSense knowledge for eMotion Identification in Conversations","created":"2020-10-06","cited_by_count":136},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130},{"id":"2310.13227","title":"ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search","created":"2023-10-20","cited_by_count":105},{"id":"2403.19154","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","created":"2024-03-28","cited_by_count":104},{"id":"2311.09469","title":"Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs","created":"2023-11-16","cited_by_count":98},{"id":"2305.14318","title":"CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models","created":"2023-05-23","cited_by_count":93},{"id":"2307.16376","title":"When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities","created":"2023-07-31","cited_by_count":90},{"id":"2402.04401","title":"Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning","created":"2024-02-06","cited_by_count":90},{"id":"2404.01869","title":"Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey","created":"2024-04-02","cited_by_count":83},{"id":"2202.13047","title":"AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation","created":"2022-02-26","cited_by_count":79},{"id":"2406.10471","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","created":"2024-06-15","cited_by_count":74},{"id":"2405.08355","title":"Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark","created":"2024-05-14","cited_by_count":63},{"id":"2305.11792","title":"Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs","created":"2023-05-19","cited_by_count":62},{"id":"2305.13712","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","created":"2023-05-23","cited_by_count":61},{"id":"2308.10278","title":"CharacterChat: Learning towards Conversational AI with Personalized Social Support","created":"2023-08-20","cited_by_count":60},{"id":"2304.06556","title":"Are LLMs All You Need for Task-Oriented Dialogue?","created":"2023-04-13","cited_by_count":54},{"id":"2304.09582","title":"Is ChatGPT Equipped with Emotional Dialogue Capabilities?","created":"2023-04-19","cited_by_count":54},{"id":"2407.00121","title":"Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks","created":"2024-06-27","cited_by_count":52},{"id":"2502.11435","title":"SMART: Self-Aware Agent for Tool Overuse Mitigation","created":"2025-02-17","cited_by_count":52},{"id":"2502.19328","title":"Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems","created":"2025-02-26","cited_by_count":51},{"id":"2401.13275","title":"Can AI Assistants Know What They Don't Know?","created":"2024-01-24","cited_by_count":50},{"id":"2203.08568","title":"In-Context Learning for Few-Shot Dialogue State Tracking","created":"2022-03-16","cited_by_count":47},{"id":"2305.14323","title":"ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models","created":"2023-05-23","cited_by_count":43},{"id":"1906.09308","title":"Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems","created":"2019-06-21","cited_by_count":42},{"id":"2105.08316","title":"CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation","created":"2021-05-18","cited_by_count":42},{"id":"2409.00557","title":"Learning to Ask: When LLM Agents Meet Unclear Instruction","created":"2024-08-31","cited_by_count":42},{"id":"2305.10172","title":"Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations","created":"2023-05-17","cited_by_count":41},{"id":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40},{"id":"2212.09235","title":"PAL: Persona-Augmented Emotional Support Conversation Generation","created":"2022-12-19","cited_by_count":39},{"id":"2305.09067","title":"SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting","created":"2023-05-15","cited_by_count":39},{"id":"2306.01386","title":"ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?","created":"2023-06-02","cited_by_count":38},{"id":"2205.11764","title":"D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat","created":"2022-05-24","cited_by_count":37},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36},{"id":"2402.13514","title":"Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions","created":"2024-02-21","cited_by_count":30},{"id":"2501.09959","title":"A Survey on Multi-Turn Interaction Capabilities of Large Language Models","created":"2025-01-17","cited_by_count":30},{"id":"2502.12961","title":"Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger","created":"2025-02-18","cited_by_count":30},{"id":"2305.16896","title":"MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting","created":"2023-05-26","cited_by_count":27},{"id":"1709.06136","title":"Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models","created":"2017-09-18","cited_by_count":26},{"id":"2310.14970","title":"Towards LLM-driven Dialogue State Tracking","created":"2023-10-23","cited_by_count":25},{"id":"2210.15088","title":"Personalized Dialogue Generation with Persona-Adaptive Attention","created":"2022-10-27","cited_by_count":24},{"id":"2410.19743","title":"AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction","created":"2024-10-10","cited_by_count":24},{"id":"2311.16789","title":"A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Models","created":"2023-11-28","cited_by_count":23},{"id":"2207.14627","title":"\"Do you follow me?\": A Survey of Recent Approaches in Dialogue State Tracking","created":"2022-07-29","cited_by_count":22},{"id":"2502.14642","title":"How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation","created":"2025-02-20","cited_by_count":22},{"id":"2406.12707","title":"Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction","created":"2024-06-18","cited_by_count":13},{"id":"2503.01940","title":"AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification","created":"2025-03-03","cited_by_count":13},{"id":"2204.05928","title":"Dynamic Dialogue Policy for Continual Reinforcement Learning","created":"2022-04-12","cited_by_count":12},{"id":"2004.10663","title":"Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition","created":"2020-04-22","cited_by_count":10},{"id":"2308.00085","title":"Reasoning before Responding: Integrating Commonsense-based Causality Explanation for Empathetic Response Generation","created":"2023-07-28","cited_by_count":9}],"next_cursor":"100"}