{"total":14,"rows":[{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462,"area":"agents"},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58,"area":"agents"},{"id":"2502.12532","title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","created":"2025-02-18","cited_by_count":32,"area":"agents"},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2404.05465","title":"HAMMR: HierArchical MultiModal React agents for generic VQA","created":"2024-04-08","cited_by_count":7,"area":"agents"},{"id":"2404.11459","title":"Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent","created":"2024-04-17","cited_by_count":7,"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":"2507.14730","title":"Towards Urban Planing AI Agent in the Age of Agentic AI","created":"2025-07-19","cited_by_count":5,"area":"agents"},{"id":"2510.14388","title":"Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control","created":"2025-10-16","cited_by_count":5,"area":"agents"},{"id":"2402.04631","title":"The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends","created":"2024-02-07","cited_by_count":4,"area":"agents"},{"id":"2511.21728","title":"Affective Multimodal Agents with Proactive Knowledge Grounding for Emotionally Aligned Marketing Dialogue","created":"2025-11-21","cited_by_count":4,"area":"agents"},{"id":"2412.18351","title":"Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering","created":"2024-12-24","cited_by_count":3,"area":"agents"},{"id":"2601.11637","title":"Evaluating Self-Correcting Vision Agents Through Quantitative and Qualitative Metrics","created":"2026-01-14","cited_by_count":1,"area":"agents"},{"id":"2606.16682","title":"Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents","created":"2026-06-15","cited_by_count":0,"area":"agents"}],"next_cursor":null}