{"total":58,"rows":[{"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":"2405.08355","title":"Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark","created":"2024-05-14","cited_by_count":63,"area":"agents"},{"id":"2402.15491","title":"API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs","created":"2024-02-23","cited_by_count":39,"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":"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":"2502.08820","title":"Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model","created":"2025-02-12","cited_by_count":20,"area":"agents"},{"id":"2603.03116","title":"Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation","created":"2026-03-03","cited_by_count":20,"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":"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":"2505.19428","title":"Frictional Agent Alignment Framework: Slow Down and Don't Break Things","created":"2025-05-26","cited_by_count":10,"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":"2512.24565","title":"MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use","created":"2025-12-31","cited_by_count":9,"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":"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":"2510.08623","title":"PARSE: LLM Driven Schema Optimization for Reliable Entity Extraction","created":"2025-10-08","cited_by_count":6,"area":"agents"},{"id":"2606.09461","title":"H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions","created":"2026-06-08","cited_by_count":6,"area":"agents"},{"id":"2510.17052","title":"ToolCritic: Detecting and Correcting Tool-Use Errors in Dialogue Systems","created":"2025-10-19","cited_by_count":5,"area":"agents"},{"id":"2509.23206","title":"PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness","created":"2025-09-27","cited_by_count":4,"area":"agents"},{"id":"2601.10702","title":"Grounding Agent Memory in Contextual Intent","created":"2026-01-15","cited_by_count":4,"area":"agents"},{"id":"2607.26598","title":"Living-Harness Is an Interactive-Agent Evolver","created":"2026-07-29","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":"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":"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":"2511.08835","title":"Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents","created":"2025-11-11","cited_by_count":2,"area":"agents"},{"id":"2603.25031","title":"From Stateless to Situated: Building a Psychological World for LLM-Based Agents","created":"2026-03-26","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":"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":"2607.17701","title":"ProEvent: An Event-centric Benchmark for Proactive Agents","created":"2026-07-20","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":"2406.10590","title":"LLM-Mediated Domain-Specific Voice Agents: The Case of TextileBot","created":"2024-06-15","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":"2508.15119","title":"Flexible Agent Alignment with Goal Inference from Open-Ended Dialog","created":"2025-08-20","cited_by_count":1,"area":"agents"},{"id":"2601.15290","title":"Agentic Persona Control and Task State Tracking for Realistic User Simulation in Interactive Scenarios","created":"2025-11-30","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":"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":"2605.21027","title":"Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs","created":"2026-05-20","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":"2608.27818","title":"AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics","created":"2026-08-28","cited_by_count":1,"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":"2602.05597","title":"Emulating Aggregate Human Choice Behavior and Biases with GPT Conversational Agents","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2603.24747","title":"Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach","created":"2026-03-25","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":"2606.31307","title":"When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue","created":"2026-06-30","cited_by_count":0,"area":"agents"},{"id":"2608.18085","title":"Persona-Guided LLM Agents for Task-Oriented Dialogue","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2608.26263","title":"SKILL.state: Scalable Long-Horizon Agent Skills","created":"2026-08-26","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":"2609.31047","title":"DynBranch: Speculative Subgraph Reuse for Dynamic Agentic LLM Serving","created":"2026-09-25","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":"2610.18881","title":"Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}