Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System | Paper Citation Record

Observation 7f9aa27a-b049-4b94-96e3-f84b24817a9a · outbound

This paper cites UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.285695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d8d2ca8-daa9-4a97-99b6-2ebe17933e13 · outbound

This paper cites Self-supervised monocular depth estimation from oblique uav videos,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Self-supervised monocular depth estimation from oblique uav videos,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.808370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9bb809a9-b870-464e-be9d-a52fa5e966e6 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player?.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Mmbench: Is your multi-modal model an all-around player?

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.294366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b841e4b-00be-4c80-b8d1-e36eaf831163 · outbound

This paper cites RSVQA: Visual question answering for remote sensing data,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System RSVQA: Visual question answering for remote sensing data,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.790802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3a3c2380-3bf0-4a27-b4bb-f58628874ea4 · outbound

This paper cites Vrsbench: A versatile vision-language benchmark dataset for remote sensing image understanding,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Vrsbench: A versatile vision-language benchmark dataset for remote sensing image understanding,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.302497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d6dd457-786c-4a91-ad82-2d0eaf2ca8b5 · outbound

This paper cites Xlrs-bench: Could your multimodal llms understand extremely large ultra-high-resolution remote sensing im- agery?.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Xlrs-bench: Could your multimodal llms understand extremely large ultra-high-resolution remote sensing im- agery?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.306758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a89ca7f-037a-453a-804e-7e955531adcf · outbound

This paper cites Visdrone-det2019: The vision meets drone object detection in image challenge results,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Visdrone-det2019: The vision meets drone object detection in image challenge results,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.310496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 640fa146-fb7f-43d7-868a-21f739b2b799 · outbound

This paper cites The unmanned aerial vehicle benchmark: Object detection and tracking,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System The unmanned aerial vehicle benchmark: Object detection and tracking,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.313917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87fed708-44f0-4c26-a9b4-7bac1a49038b · outbound

This paper cites Urbanvideo-bench: Benchmarking vision-language models on embodied intelligence with video data in urban spaces,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Urbanvideo-bench: Benchmarking vision-language models on embodied intelligence with video data in urban spaces,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.317202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 464fc5d6-ea0f-45df-ac38-3867bb375d1e · outbound

This paper cites Yolo26: An analysis of nms-free end to end framework for real-time object detection,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Yolo26: An analysis of nms-free end to end framework for real-time object detection,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.321735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c6b33d9-675d-4adf-b42d-85cad76e03b9 · outbound

This paper cites DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:31:28.273071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7eb40ff3-37a0-452f-bdb1-e2e3a9baebc9 · outbound

This paper cites UAV-Based Intelligent Traffic Surveillance System: Real-Time Vehicle Detection, Classification, Tracking, and Behavioral Analysis.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System UAV-Based Intelligent Traffic Surveillance System: Real-Time Vehicle Detection, Classification, Tracking, and Behavioral Analysis

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:31:28.256406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c5535b51-d8d8-45ca-acd9-56bfdc6999df · outbound

This paper cites Global–local fusion with semantic information-guidance for accurate small object detection in UA V aerial images,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Global–local fusion with semantic information-guidance for accurate small object detection in UA V aerial images,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.754303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fb6fa9b1-0cfa-4144-b5c5-b25e30f8dc14 · outbound

This paper cites Detection-driven exposure-correction network for nighttime drone-view object detection,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Detection-driven exposure-correction network for nighttime drone-view object detection,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.743869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fe4a1849-3b77-43c0-bc41-728c15125cf9 · outbound

This paper cites Wheatai v1. 0: An ai-powered high throughput wheat phenotyping platform,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Wheatai v1. 0: An ai-powered high throughput wheat phenotyping platform,

Reference 15

Resolution: verified exact; raw_fallback, observed 2026-08-16T00:31:28.241058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5955763a-8ea9-4a7c-bff9-6350ce4d1866 · outbound

This paper cites Maizestandcounting (masc): Auto- mated and accurate maize stand counting from uav imagery using image processing and deep learning,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Maizestandcounting (masc): Auto- mated and accurate maize stand counting from uav imagery using image processing and deep learning,

Reference 16

Resolution: verified exact; raw_fallback, observed 2026-08-16T00:31:28.172952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1723bf71-7461-4e21-89e6-c0f520b7ada7 · outbound

This paper cites Panoptic Segmentation of Environmental UAV Images : Litter Beach.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Panoptic Segmentation of Environmental UAV Images : Litter Beach

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:31:28.103112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1463b128-b880-4252-b191-54da15b7b961 · outbound

This paper cites Codrone: Autonomous drone navigation assisted by edge and cloud foundation models,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Codrone: Autonomous drone navigation assisted by edge and cloud foundation models,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.732188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4f751f18-66c7-480a-9987-db861d7ee20f · outbound

This paper cites Generalization evaluation of deep stereo matching methods for uav-based forestry applications,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Generalization evaluation of deep stereo matching methods for uav-based forestry applications,

Reference 19

Resolution: verified exact; raw_fallback, observed 2026-08-16T00:31:28.086685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 79eb51ea-553b-4315-9b42-3ef0cac51642 · outbound

This paper cites Precise depth estimation by calculating affine transformation parameters,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Precise depth estimation by calculating affine transformation parameters,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.721023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 09e7cb06-9bfb-448b-9116-d3c41726bbb4 · outbound

This paper cites FLDet: Faster and lighter aerial object detector,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System FLDet: Faster and lighter aerial object detector,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.709630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 56d17056-53ce-490c-86ff-a2ebdc65618b · outbound

This paper cites TGCADNet: Text-guided context-aware detection via CLIP for small objects in UA V scenes,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System TGCADNet: Text-guided context-aware detection via CLIP for small objects in UA V scenes,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.698749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 15e38d26-f309-47ef-9b33-9853ce22c986 · outbound

This paper cites Detect anything via next point prediction,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Detect anything via next point prediction,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.368435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed7f1e47-46c9-43cf-b8d3-f0a3686c3224 · outbound

This paper cites Visdrone-det2021: The vision meets drone object detection challenge results,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Visdrone-det2021: The vision meets drone object detection challenge results,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.687182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 63aa5ea4-565f-430f-8b2b-739758c52de2 · outbound

This paper cites Dota: A large-scale dataset for object detection in aerial images,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Dota: A large-scale dataset for object detection in aerial images,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.375228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a230828-e41d-42b0-97d6-2910a398df01 · outbound

This paper cites UAVScenes: A Multi-Modal Dataset for UAVs.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System UAVScenes: A Multi-Modal Dataset for UAVs

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:31:27.947353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d1370554-1d96-45dc-9cd9-f57e0e86abb7 · outbound

This paper cites Dyfo: A training-free dynamic focus visual search for enhancing lmms in fine-grained visual understanding,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Dyfo: A training-free dynamic focus visual search for enhancing lmms in fine-grained visual understanding,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.670772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b20e04b2-c8af-4885-aab2-9b3f0944e60b · outbound

This paper cites PyVision: Agentic Vision with Dynamic Tooling.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System PyVision: Agentic Vision with Dynamic Tooling

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.386319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e92c2adc-7ac7-4b10-a9b4-e041a1c76188 · outbound

This paper cites Multi-agent constraint factorization reveals latent invariant solution structure,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Multi-agent constraint factorization reveals latent invariant solution structure,

Reference 29

Resolution: verified exact; raw_fallback, observed 2026-08-16T00:31:27.911979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0240dbda-b017-4657-bb9d-48a75908c004 · outbound

This paper cites MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.393535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f77dffa-9378-4dc2-9d58-45e4bbd1d2fb · outbound

This paper cites Agent Identity URI Scheme: Topology-Independent Naming and Capability-Based Discovery for Multi-Agent Systems.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Agent Identity URI Scheme: Topology-Independent Naming and Capability-Based Discovery for Multi-Agent Systems

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:31:27.837504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5e656d98-fe91-4c3c-a84a-a59c2340c1e3 · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.400755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee9d8d0e-f173-40d9-85e5-ca2bb8288c96 · outbound

This paper cites Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.404493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90fd04e1-a0c0-42ad-ab75-0b9a42958c0f · outbound

This paper cites The orchestration of multi- agent systems: Architectures, protocols, and enterprise adoption,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System The orchestration of multi- agent systems: Architectures, protocols, and enterprise adoption,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.408106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f790320e-103e-4a76-93a3-20faed97d1bc · outbound

This paper cites Motion-to-response content generation via multi-agent ai sys- tem with real-time safety verification,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Motion-to-response content generation via multi-agent ai sys- tem with real-time safety verification,

Reference 35

Resolution: verified exact; raw_fallback, observed 2026-08-16T00:31:27.738154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fc6fa419-fd49-4951-9550-9907b2548d11 · outbound

This paper cites Agentgc: Evolutionary learning-based lossless compres- sion for genomics data with llm-driven multiple agent,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Agentgc: Evolutionary learning-based lossless compres- sion for genomics data with llm-driven multiple agent,

Reference 36

Resolution: verified exact; raw_fallback, observed 2026-08-16T00:31:27.668711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 20d81a4c-eb67-4652-a8e9-22648a8d5da1 · outbound

This paper cites React: Synergizing reasoning and acting in language models,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System React: Synergizing reasoning and acting in language models,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.418416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48bdafe8-15ee-4f2e-9a24-d0b1c20a6d47 · outbound

This paper cites Au-air: A multi-modal unmanned aerial vehicle dataset for low altitude traffic surveillance,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Au-air: A multi-modal unmanned aerial vehicle dataset for low altitude traffic surveillance,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.421760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 563514e4-d2b0-4ed3-b14e-ab8460831e53 · outbound

This paper cites Webuav-3m: A benchmark for unveiling the power of million- scale deep uav tracking,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Webuav-3m: A benchmark for unveiling the power of million- scale deep uav tracking,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.646994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 20a9576c-9880-4321-9ec5-6203ca32852d · outbound

This paper cites Visdrone-det2019: The vision meets drone object detection in image challenge results,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Visdrone-det2019: The vision meets drone object detection in image challenge results,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.636084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation feb753c5-a7bc-4337-8017-10c5bc9c8518 · outbound

This paper cites Semantic drone dataset,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Semantic drone dataset,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.624675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a00e629e-3715-4fe6-9515-728a596eea46 · outbound

This paper cites Drone-based rgb-infrared cross- modality vehicle detection via uncertainty-aware learning,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Drone-based rgb-infrared cross- modality vehicle detection via uncertainty-aware learning,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.434431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6df930a-9bab-40b1-a3b1-b6a47abadf9b · outbound

This paper cites Vdd: Varied drone dataset for semantic segmentation,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Vdd: Varied drone dataset for semantic segmentation,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.437160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af02ae8d-c27e-4005-b924-02e5f0c22608 · outbound

This paper cites Large-scale structure from motion with semantic constraints of aerial images,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Large-scale structure from motion with semantic constraints of aerial images,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.600535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e0569390-b131-47a0-868e-1a52a25b3cc2 · outbound

This paper cites Uavid: A semantic segmentation dataset for uav imagery,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Uavid: A semantic segmentation dataset for uav imagery,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.443026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3a45f6-48e8-4105-85ea-ef5d7cf47f34 · outbound

This paper cites Wilduav: Monocular uav dataset for depth estimation tasks,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Wilduav: Monocular uav dataset for depth estimation tasks,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.583292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0357ab5e-5570-4f44-8424-838611675601 · outbound

This paper cites HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.449187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d27f48d6-ab96-45ad-adda-985ca6d69a29 · outbound

This paper cites Graph regularized flow attention network for video animal counting from drones,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Graph regularized flow attention network for video animal counting from drones,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.573252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1a89ec76-721b-4035-b1e6-9650f231495d · outbound

This paper cites A benchmark and simulator for uav tracking,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System A benchmark and simulator for uav tracking,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.562943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9f5c44dc-e5d8-445a-9951-12c95cf72dd1 · outbound

This paper cites Depth Anything 3: Recovering the Visual Space from Any Views.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Depth Anything 3: Recovering the Visual Space from Any Views

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.460565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dba91f5-e108-4d0c-8b3b-598d9b3bc340 · outbound

This paper cites Qwen3-VL Technical Report.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Qwen3-VL Technical Report

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.465038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b50537b-3c82-40a7-85e7-c17eb5863428 · outbound

This paper cites GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.468674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4cc5f43-ba47-4f60-8dcc-e957330a89fa · outbound

This paper cites Qwen3.5: Accelerating productivity with native multimodal agents,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Qwen3.5: Accelerating productivity with native multimodal agents,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T00:31:27.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 755e62de-a8c8-4c5b-9135-4de8b5fc0911 · outbound

This paper cites Introducing gpt-5.2,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Introducing gpt-5.2,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.545105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b5130d4f-40a2-40ff-bf9e-f9662f5e1391 · outbound

This paper cites Gemini 3 pro and gemini 3 flash models,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Gemini 3 pro and gemini 3 flash models,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.534338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 077a1e73-0aea-438a-9d58-29d830c89b29 · outbound

This paper cites Qwen-agent: An agent framework based on qwen,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Qwen-agent: An agent framework based on qwen,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.523597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c374b9b-6025-43a5-bdcc-974d87661716 · outbound

This paper cites Choice: Benchmarking the remote sensing capabilities of large vision-language models,.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Choice: Benchmarking the remote sensing capabilities of large vision-language models,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.511958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 27a23c46-c6a7-45e3-953a-b5648a009d0f · outbound

This paper cites an unresolved cited work.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:31:28.488005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 34a35d45-76de-4464-8aa6-1bf139429487 · outbound

This paper cites ◦Classify the object in region{<x 1><y1><x2><y2>}.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System ◦Classify the object in region{<x 1><y1><x2><y2>}

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.476748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 40eafc3f-ee13-4d5d-aa49-24cf7d65df1b · outbound

This paper cites ◦Count all the{object}in this picture.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System ◦Count all the{object}in this picture

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.464426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5accec8a-da81-45ad-852b-8bfed2612d65 · outbound

This paper cites ◦Which color does the{object}in{<x 1><y1><x2><y2>}have? ◦Identify the driving direction (relative to the camera) of the{object}in{<x 1><y1><x2><y2>}.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System ◦Which color does the{object}in{<x 1><y1><x2><y2>}have? ◦Identify the driving direction (relative to the camera) of the{object}in{<x 1><y1><x2><y2>}

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.453116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 01ec38de-7eea-4f1e-a256-e2657a007991 · outbound

This paper cites an unresolved cited work.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:31:28.442992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ccc06e18-cd83-474a-bdae-19be10cdb9c7 · outbound

This paper cites Yes", "No.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Yes", "No

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.433322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2fbf2747-4dc0-4ae0-90bc-2abdb12b614d · outbound

This paper cites Q”, “O”, and “A.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System Q”, “O”, and “A

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.422020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 803ab6ca-615c-4a4d-aa5f-54e44704ff68 · outbound

This paper cites He is currently a Professor with the College of Future In- formation Technology, Fudan University, Shanghai, China.

Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System He is currently a Professor with the College of Future In- formation Technology, Fudan University, Shanghai, China

Reference 2013

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:31:28.499622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers