{"total":27,"rows":[{"id":"2507.07998","title":"PyVision: Agentic Vision with Dynamic Tooling","created":"2025-07-10","cited_by_count":79,"area":"agents"},{"id":"2604.07430","title":"HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents","created":"2026-04-08","cited_by_count":18,"area":"agents"},{"id":"2602.20739","title":"PyVision-RL: Forging Open Agentic Vision Models via RL","created":"2026-02-24","cited_by_count":16,"area":"agents"},{"id":"2606.20515","title":"S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence","created":"2026-06-18","cited_by_count":11,"area":"agents"},{"id":"2505.07634","title":"Neural Brain: A Neuroscience-inspired Framework for Embodied Agents","created":"2025-05-12","cited_by_count":10,"area":"agents"},{"id":"2607.12894","title":"Hy-Embodied-VLM-1.0: Efficient Physical-World Agents","created":"2026-07-14","cited_by_count":8,"area":"agents"},{"id":"2508.17198","title":"From reactive to cognitive: brain-inspired spatial intelligence for embodied agents","created":"2025-08-24","cited_by_count":7,"area":"agents"},{"id":"2507.00914","title":"Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications","created":"2025-07-01","cited_by_count":4,"area":"agents"},{"id":"2602.01640","title":"A2Eval: Agentic and Automated Evaluation for Embodied Brain","created":"2026-02-02","cited_by_count":4,"area":"agents"},{"id":"2502.18822","title":"Data-Efficient Multi-Agent Spatial Planning with LLMs","created":"2025-02-26","cited_by_count":3,"area":"agents"},{"id":"2505.20148","title":"MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents","created":"2025-05-26","cited_by_count":3,"area":"agents"},{"id":"2506.04217","title":"OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis","created":"2025-06-04","cited_by_count":3,"area":"agents"},{"id":"2602.09012","title":"Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense","created":"2026-02-09","cited_by_count":3,"area":"agents"},{"id":"2606.08992","title":"SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning","created":"2026-06-08","cited_by_count":3,"area":"agents"},{"id":"2508.07033","title":"$\\mathcal{P}^3$: Toward Versatile Embodied Agents","created":"2025-08-09","cited_by_count":2,"area":"agents"},{"id":"2510.08173","title":"NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2511.12676","title":"BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections","created":"2025-11-16","cited_by_count":2,"area":"agents"},{"id":"2608.03979","title":"Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2512.19016","title":"DREAM: Dynamic Red-teaming across Environments for AI Models","created":"2025-12-22","cited_by_count":1,"area":"agents"},{"id":"2512.24504","title":"Thinking on Maps: How Foundation Model Agents Explore, Remember, and Reason Map Environments","created":"2025-12-30","cited_by_count":1,"area":"agents"},{"id":"2603.19166","title":"Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2609.24526","title":"ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination","created":"2026-09-21","cited_by_count":1,"area":"agents"},{"id":"2603.29798","title":"SceneTeract: Probing and Improving Agent-Aware Activity Reasoning in 3D Indoor Scenes","created":"2026-03-31","cited_by_count":0,"area":"agents"},{"id":"2606.21337","title":"DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"id":"2610.14158","title":"Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.18355","title":"ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.20560","title":"PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}