Paper Citation Record · LEDGER

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes

As of 4 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2605.31148.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2605.31148 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T22:47:46.542267Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

42 of 42 outbound references displayed

verified exact13
verified fuzzy0
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9defce82-bb36-428b-bbcc-9d34b1558c03 · outbound

This paper cites Placeit3d: Language-guided object placement in real 3d scenes.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Placeit3d: Language-guided object placement in real 3d scenes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c88463bc-9241-4132-9c8e-455242d8ecf2 · outbound

This paper cites Gemini-3.1 pro.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Gemini-3.1 pro

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 395fc00e-7781-4061-a7c8-bff1666a8a2b · outbound

This paper cites Scanedit: Hierarchically-guided functional 3d scan editing.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Scanedit: Hierarchically-guided functional 3d scan editing

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 183ade7e-ec5a-4b58-a3d4-b0274a29fa85 · outbound

This paper cites Repurposing 3D Generative Model for Autoregressive Layout Generation.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Repurposing 3D Generative Model for Autoregressive Layout Generation

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-28T22:52:45.649456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cb976fd4-dd60-4d99-b28e-56a9e309d5db · outbound

This paper cites Layoutgpt: Compositional visual planning and generation with large language models.Advances in Neural Information Processing Systems, 36:18225–18250, 2023.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Layoutgpt: Compositional visual planning and generation with large language models.Advances in Neural Information Processing Systems, 36:18225–18250, 2023

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58e58408-69c2-4b73-bdf8-af4a224bb64d · outbound

This paper cites GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-28T22:52:45.651730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 527711ea-d5d9-43bc-a49a-6af4ab464910 · outbound

This paper cites Fireplace: Geometric refinements of llm common sense reasoning for 3d object placement.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Fireplace: Geometric refinements of llm common sense reasoning for 3d object placement

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 889aa6f0-bf32-4c0d-a6bb-86e02a2f4be3 · outbound

This paper cites Spatial-dise: A unified benchmark for evaluating spatial reasoning in vision-language models.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Spatial-dise: A unified benchmark for evaluating spatial reasoning in vision-language models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:52:45.654255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4e520516-14ae-456a-a8f0-c68dd39449be · outbound

This paper cites Do you see me: A multidimensional benchmark for evaluating visual perception in multimodal llms.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Do you see me: A multidimensional benchmark for evaluating visual perception in multimodal llms

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41cfa93a-29cd-418a-ab55-bd0bb52586af · outbound

This paper cites Viewspatial-bench: Evaluating multi-perspective spatial localization in vision-language models.ArXiv, abs/2505.21500.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Viewspatial-bench: Evaluating multi-perspective spatial localization in vision-language models.ArXiv, abs/2505.21500

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:52:45.656882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9c1c9787-8eb6-4c9b-8ecf-4579c5edccf8 · outbound

This paper cites Embodied agent interface: Benchmarking llms for embodied decision making.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Embodied agent interface: Benchmarking llms for embodied decision making

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34651ba5-d003-4d40-9e8f-04ed8d779eda · outbound

This paper cites Core Knowledge Deficits in Multi-Modal Language Models.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Core Knowledge Deficits in Multi-Modal Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:16:01.160739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 87be5ba3-0d53-4c46-a9cc-05ccccf50ec2 · outbound

This paper cites Spatial reasoning in multimodal large language models: A survey of tasks, benchmarks and methods.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Spatial reasoning in multimodal large language models: A survey of tasks, benchmarks and methods

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:16:01.155277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 402da64e-ed34-4f2a-83f1-6e795d61cbe1 · outbound

This paper cites Openeqa: Embodied question answering in the era of foundation models.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Openeqa: Embodied question answering in the era of foundation models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28fc1866-c84b-4107-b232-3b95bced9820 · outbound

This paper cites Gpt-5.4.https://openai.com/index/introducing-gpt-5-4/, 2026.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Gpt-5.4.https://openai.com/index/introducing-gpt-5-4/, 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c33b1710-2012-4dc1-8b5f-fb3176e6aa64 · outbound

This paper cites Qwen3.6-27B: Flagship-level coding in a 27B dense model, April 2026.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Qwen3.6-27B: Flagship-level coding in a 27B dense model, April 2026

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8adb51d0-8853-4ffe-9bde-69537a55485b · outbound

This paper cites Qwen3.6-35B-A3B: Agentic coding power, now open to all, April 2026.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Qwen3.6-35B-A3B: Agentic coding power, now open to all, April 2026

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d137ed69-6c52-4aad-b193-8cee47b04f23 · outbound

This paper cites Vision language models are blind: Failing to translate detailed visual features into words.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Vision language models are blind: Failing to translate detailed visual features into words

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:52:45.666857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d5fbae3c-6a59-457f-bf9d-62b66a9d59b1 · outbound

This paper cites Does Spatial Cognition Emerge in Frontier Models?.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Does Spatial Cognition Emerge in Frontier Models?

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:16:01.154262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7d6b5f4d-bd6e-4fd2-ae96-bc525ddac2ef · outbound

This paper cites Layoutvlm: Differentiable optimization of 3d layout via vision- language models.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Layoutvlm: Differentiable optimization of 3d layout via vision- language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3abb5795-8fb8-4a04-83e3-f8def5e15c0f · outbound

This paper cites SpaceVista: All-Scale Visual Spatial Reasoning from mm to km.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes SpaceVista: All-Scale Visual Spatial Reasoning from mm to km

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-01T19:16:01.156980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 39770aa2-0783-4818-b3e7-fbb41d9fc165 · outbound

This paper cites Kimi k2.5: Visual agentic intelligence, 2026.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Kimi k2.5: Visual agentic intelligence, 2026

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 062363fa-4c4f-4810-9295-82c8a5ebe7c1 · outbound

This paper cites Is a picture worth a thousand words? delving into spatial reasoning for vision language models.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Is a picture worth a thousand words? delving into spatial reasoning for vision language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eec17679-0fa4-4514-8190-c4f898e91af4 · outbound

This paper cites Raisecity: A multimodal agent framework for reality-aligned 3d world generation at city-scale.arXiv preprint arXiv:2511.18005, 2025.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Raisecity: A multimodal agent framework for reality-aligned 3d world generation at city-scale.arXiv preprint arXiv:2511.18005, 2025

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:52:45.667323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d6a48103-f77f-449d-a06a-aa163513ea57 · outbound

This paper cites Embodied scene understanding for vision language models via metavqa.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Embodied scene understanding for vision language models via metavqa

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a9bc7f3-b327-4305-a735-fd06fa2f5f9a · outbound

This paper cites Site: towards spatial intelligence thorough evaluation.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Site: towards spatial intelligence thorough evaluation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c24158f4-458a-4e7e-9f64-0924bf6b9e9f · outbound

This paper cites Spatial457: A diagnostic benchmark for 6d spatial reasoning of large mutimodal models.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Spatial457: A diagnostic benchmark for 6d spatial reasoning of large mutimodal models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2325f0d-1813-431c-8b06-bdc3f95f59af · outbound

This paper cites Visual room rearrange- ment.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Visual room rearrange- ment

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35661b05-bba2-4e93-90c8-8ca555bb050c · outbound

This paper cites Spatialtree : How spatial abilities branch out in MLLMs.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Spatialtree : How spatial abilities branch out in MLLMs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1a7da44-6e1a-4a81-acc0-c9c1886e1067 · outbound

This paper cites CityCube: Benchmarking cross-view spatial reasoning on vision-language models in urban environments.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes CityCube: Benchmarking cross-view spatial reasoning on vision-language models in urban environments

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:52:45.661726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4afe071f-2a15-43f4-8ea3-71ba977465bb · outbound

This paper cites Defining and evaluating visual language models’ basic spatial abilities: A perspective from psychometrics.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Defining and evaluating visual language models’ basic spatial abilities: A perspective from psychometrics

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc9d0108-100e-4a2e-9837-0e8876ac5551 · outbound

This paper cites Thinking in space: How multimodal large language models see, remember, and recall spaces.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Thinking in space: How multimodal large language models see, remember, and recall spaces

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75bb97db-8f79-4e4b-9735-31f12aaee948 · outbound

This paper cites Holodeck: Language guided generation of 3d embodied ai environments.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Holodeck: Language guided generation of 3d embodied ai environments

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3e8ec7c-3825-49d0-b65b-4c3078aea8ec · outbound

This paper cites Spatial mental modeling from limited views.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Spatial mental modeling from limited views

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4e13388-034e-4a2c-9609-348c0e85f46d · outbound

This paper cites arXiv:2509.18905 (2025) 6, 9, 17.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes arXiv:2509.18905 (2025) 6, 9, 17

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T22:52:45.662040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 15ad3398-d24d-48d0-8787-6dd67acdcac4 · outbound

This paper cites Et-plan- bench: Embodied task-level planning benchmark towards spatial-temporal cognition with foundation models.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Et-plan- bench: Embodied task-level planning benchmark towards spatial-temporal cognition with foundation models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecb79f32-8aa3-4e05-9154-9da03777d856 · outbound

This paper cites Theory of space: Can foundation models construct spatial beliefs through active exploration? InThe Fourteenth International Conference on Learning Representations, 2026.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Theory of space: Can foundation models construct spatial beliefs through active exploration? InThe Fourteenth International Conference on Learning Representations, 2026

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cdeccad-6bfc-4953-b7e2-69469410851f · outbound

This paper cites SPHERE: Unveiling spatial blind spots in vision-language models through hierarchical evaluation.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes SPHERE: Unveiling spatial blind spots in vision-language models through hierarchical evaluation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 331979fc-5656-4070-abbf-1e0d018efdb4 · outbound

This paper cites an unresolved cited work.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1670f69-e4a6-4a2d-96d0-9f1da2a7c030 · outbound

This paper cites Cityeqa: A hierarchical llm agent on embodied question answering benchmark in city space.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Cityeqa: A hierarchical llm agent on embodied question answering benchmark in city space

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-28T22:47:46.542267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e187df64-a2be-4430-b8dd-084a787d2d91 · outbound

This paper cites 3d-layout-r1: Structured reasoning for language-instructed spatial editing.arXiv preprint arXiv:2603.22279, 2026.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes 3d-layout-r1: Structured reasoning for language-instructed spatial editing.arXiv preprint arXiv:2603.22279, 2026

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:52:45.664638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2c07ae8b-5559-4680-848b-53e748b90322 · outbound

This paper cites InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-06-28T22:52:45.669731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

No inbound Pith citation observations are available.