{"total":70,"rows":[{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402,"area":"agents"},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251,"area":"agents"},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2305.13040","title":"SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents","created":"2023-05-22","cited_by_count":71,"area":"agents"},{"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":"2405.00823","title":"WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting","created":"2024-05-01","cited_by_count":53,"area":"agents"},{"id":"2402.10466","title":"Large Language Models as Zero-shot Dialogue State Tracker through Function Calling","created":"2024-02-16","cited_by_count":34,"area":"agents"},{"id":"2503.00564","title":"ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models","created":"2025-03-01","cited_by_count":34,"area":"agents"},{"id":"2410.18447","title":"ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis","created":"2024-10-24","cited_by_count":30,"area":"agents"},{"id":"2507.05639","title":"ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?","created":"2025-07-08","cited_by_count":27,"area":"agents"},{"id":"2405.13037","title":"Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation","created":"2024-05-17","cited_by_count":24,"area":"agents"},{"id":"2412.08445","title":"TapeAgents: a Holistic Framework for Agent Development and Optimization","created":"2024-12-11","cited_by_count":13,"area":"agents"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2402.01018","title":"HR-MultiWOZ: A Task Oriented Dialogue (TOD) Dataset for HR LLM Agent","created":"2024-02-01","cited_by_count":12,"area":"agents"},{"id":"2407.03884","title":"ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents","created":"2024-07-04","cited_by_count":12,"area":"agents"},{"id":"2603.00656","title":"InfoPO: Information-Driven Policy Optimization for User-Centric Agents","created":"2026-02-28","cited_by_count":12,"area":"agents"},{"id":"2411.09972","title":"Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems","created":"2024-11-15","cited_by_count":11,"area":"agents"},{"id":"2411.00427","title":"DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems","created":"2024-11-01","cited_by_count":9,"area":"agents"},{"id":"2510.07043","title":"COMPASS: Benchmarking Constrained Optimization in LLM Agents","created":"2025-10-08","cited_by_count":9,"area":"agents"},{"id":"2601.22027","title":"CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2205.03692","title":"Towards a Progression-Aware Autonomous Dialogue Agent","created":"2022-05-07","cited_by_count":7,"area":"agents"},{"id":"2509.04472","title":"RECAP: REwriting Conversations for Intent Understanding in Agentic Planning","created":"2025-08-29","cited_by_count":7,"area":"agents"},{"id":"2608.19652","title":"Can Agent Memory Systems Track Evolving State?","created":"2026-08-20","cited_by_count":7,"area":"agents"},{"id":"2409.04617","title":"Sparse Rewards Can Self-Train Dialogue Agents","created":"2024-09-06","cited_by_count":6,"area":"agents"},{"id":"2501.05255","title":"CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing","created":"2025-01-09","cited_by_count":6,"area":"agents"},{"id":"2506.12266","title":"The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs","created":"2025-06-13","cited_by_count":6,"area":"agents"},{"id":"2508.12630","title":"Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Context","created":"2025-08-18","cited_by_count":5,"area":"agents"},{"id":"2510.21244","title":"VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series","created":"2025-10-24","cited_by_count":5,"area":"agents"},{"id":"2509.06341","title":"Evaluating Multi-Turn Bargain Skills in LLM-Based Seller Agent","created":"2025-09-08","cited_by_count":4,"area":"agents"},{"id":"2510.01609","title":"AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence","created":"2025-10-02","cited_by_count":4,"area":"agents"},{"id":"2507.19543","title":"Agent WARPP: Workflow Adherence via Runtime Parallel Personalization","created":"2025-07-23","cited_by_count":3,"area":"agents"},{"id":"2508.19163","title":"MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation","created":"2025-08-26","cited_by_count":3,"area":"agents"},{"id":"2603.28569","title":"CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments","created":"2026-03-30","cited_by_count":3,"area":"agents"},{"id":"2609.20152","title":"MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2407.05674","title":"Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets","created":"2024-07-08","cited_by_count":2,"area":"agents"},{"id":"2409.18538","title":"A Survey on Complex Tasks for Goal-Directed Interactive Agents","created":"2024-09-27","cited_by_count":2,"area":"agents"},{"id":"2505.01592","title":"AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents","created":"2025-05-02","cited_by_count":2,"area":"agents"},{"id":"2601.11658","title":"Towards AGI A Pragmatic Approach Towards Self Evolving Agent","created":"2026-01-15","cited_by_count":2,"area":"agents"},{"id":"2604.09285","title":"SAGE: A Service Agent Graph-guided Evaluation Benchmark","created":"2026-04-10","cited_by_count":2,"area":"agents"},{"id":"2604.17886","title":"Latent Preference Modeling for Multi-Session Personalized Tool Calling","created":"2026-04-20","cited_by_count":2,"area":"agents"},{"id":"2604.27891","title":"In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks","created":"2026-04-30","cited_by_count":2,"area":"agents"},{"id":"2605.06897","title":"MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes","created":"2026-05-07","cited_by_count":2,"area":"agents"},{"id":"2307.07255","title":"Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems","created":"2023-07-14","cited_by_count":1,"area":"agents"},{"id":"2310.09773","title":"RSVP: Customer Intent Detection via Agent Response Contrastive and Generative Pre-Training","created":"2023-10-15","cited_by_count":1,"area":"agents"},{"id":"2405.17840","title":"Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents","created":"2024-05-28","cited_by_count":1,"area":"agents"},{"id":"2410.11239","title":"HR-Agent: A Task-Oriented Dialogue (TOD) LLM Agent Tailored for HR Applications","created":"2024-10-15","cited_by_count":1,"area":"agents"},{"id":"2502.19610","title":"Program Synthesis Dialog Agents for Interactive Decision-Making","created":"2025-02-26","cited_by_count":1,"area":"agents"},{"id":"2508.15119","title":"Flexible Agent Alignment with Goal Inference from Open-Ended Dialog","created":"2025-08-20","cited_by_count":1,"area":"agents"},{"id":"2511.19780","title":"NOEM$^{3}$A: a Neuro-symbolic Ontology-Enhanced Method for Multi-intent understanding in Mobile Agents","created":"2025-11-24","cited_by_count":1,"area":"agents"},{"id":"2602.18764","title":"The Convergence of Schema-Guided Dialogue Systems and the Model Context Protocol","created":"2026-02-21","cited_by_count":1,"area":"agents"},{"id":"2602.22697","title":"Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue","created":"2026-02-26","cited_by_count":1,"area":"agents"},{"id":"2603.01059","title":"GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant","created":"2026-03-01","cited_by_count":1,"area":"agents"},{"id":"2605.19077","title":"ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking","created":"2026-05-18","cited_by_count":1,"area":"agents"},{"id":"2607.18316","title":"Binding Drift in Multi-Step Tool-Augmented Agents","created":"2026-07-17","cited_by_count":1,"area":"agents"},{"id":"2608.24588","title":"IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2608.27818","title":"AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics","created":"2026-08-28","cited_by_count":1,"area":"agents"},{"id":"2507.03726","title":"Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language Models","created":"2025-07-04","cited_by_count":0,"area":"agents"},{"id":"2601.11854","title":"ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems","created":"2026-01-17","cited_by_count":0,"area":"agents"},{"id":"2604.10968","title":"YIELD: A Large-Scale Dataset and Evaluation Framework for Information Elicitation Agents","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.04449","title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2606.24783","title":"Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2606.28187","title":"GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems","created":"2026-06-26","cited_by_count":0,"area":"agents"},{"id":"2607.11707","title":"An Explainable Agentic System for Detection of Conversational Scams with Summary-Based Memory","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2608.05729","title":"Unified Agent: Managing Interactions across Devices","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.15755","title":"Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents","created":"2026-08-16","cited_by_count":0,"area":"agents"},{"id":"2608.20566","title":"AgentDecarbonizer: Carbon-Aware Execution for AI Agents","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2609.00434","title":"SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2610.12975","title":"SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.20195","title":"What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}