{"total":29,"rows":[{"id":"2604.04847","title":"Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency","created":"2026-04-06","cited_by_count":37,"area":"agents"},{"id":"2505.20277","title":"OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction","created":"2025-05-26","cited_by_count":14,"area":"agents"},{"id":"2510.04017","title":"Zephyrus: An Agentic Framework for Weather Science","created":"2025-10-05","cited_by_count":10,"area":"agents"},{"id":"2502.15218","title":"ESPnet-SpeechLM: An Open Speech Language Model Toolkit","created":"2025-02-21","cited_by_count":9,"area":"agents"},{"id":"2512.14234","title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","created":"2025-12-16","cited_by_count":6,"area":"agents"},{"id":"2509.11914","title":"EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models","created":"2025-09-15","cited_by_count":5,"area":"agents"},{"id":"2508.02013","title":"SpeechRole: A Large-Scale Dataset and Benchmark for Evaluating Speech Role-Playing Agents","created":"2025-08-04","cited_by_count":4,"area":"agents"},{"id":"2509.00078","title":"ChipChat: Low-Latency Cascaded Conversational Agent in MLX","created":"2025-08-26","cited_by_count":4,"area":"agents"},{"id":"2602.14048","title":"ProAct: Harnessing Streaming Motion Generation and Agentic Reasoning for Real-Time Embodied Social Interaction","created":"2026-02-15","cited_by_count":3,"area":"agents"},{"id":"2608.13831","title":"VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents","created":"2026-08-13","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":"2507.19361","title":"SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models","created":"2025-07-25","cited_by_count":2,"area":"agents"},{"id":"2606.13544","title":"Adaptive Turn-Taking for Real-time Multi-Party Voice Agents","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2609.19334","title":"A frontend-backend architecture for tool calls in full-duplex speech models","created":"2026-09-16","cited_by_count":2,"area":"agents"},{"id":"2607.18171","title":"FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2608.16053","title":"Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech","created":"2026-08-17","cited_by_count":1,"area":"agents"},{"id":"2609.03423","title":"DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.34247","title":"SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2510.22610","title":"Everything Counts: The Managed Omnirelevance of Speech in Human-Voice Agent Interaction","created":"2025-10-26","cited_by_count":0,"area":"agents"},{"id":"2607.26410","title":"Voice Memory for Agentic Speech Recognition","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2609.30798","title":"Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomes","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.31847","title":"Omni-IO Skills: Harnessing Your Agent Omni-Native","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.31967","title":"IndicFDB: Benchmarking Full-Duplex Voice Agents across Indian Languages","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.35427","title":"LLMs are General Asynchronous Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38232","title":"When Does a Spoken Agent Have Enough Evidence to Act? The PACT-SLM Contract Test","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.00316","title":"DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.10787","title":"NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.11299","title":"DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.15390","title":"From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}