Pith. sign in

Paper Citation Record · LEDGER

VLMgineer: Vision Language Models as Robotic Toolsmiths

As of 9 August 2026, this Paper Citation Record lists 98 of 98 outbound references and 3 inbound Pith citation observations for arXiv:2507.12644.

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

pith.paper-citation-record.v1
2507.12644 v1

Coverage vector

measured 98 of 98 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:49:11.453392Z

measured 101 of 101 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T07:27:03.967235Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T21:28:58.449574Z

Reference resolution

98 of 98 outbound references displayed

  • verified exact9
  • verified fuzzy44
  • unresolved45
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d25b8a73-ccf8-4ed1-ac51-9ea4e46466bf · outbound

This paper cites RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools.

VLMgineer: Vision Language Models as Robotic Toolsmiths RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T16:48:59.301746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:48:59.301746Z digest=sha256:e7e8610b9893615cfe0953762ab931feaf80dbeb7c9e29cb4a017fcac5953024

Observation e66e9c00-8efd-4ffe-a29e-e21254852005 · outbound

This paper cites Learning generalizable tool-use skills through trajectory generation,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning generalizable tool-use skills through trajectory generation,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T16:48:59.372081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:48:59.372081Z digest=sha256:f74fbd87bf7c98fae1e6b394a63b03c03551e88484bd7a30e1f753d66d1fa23f

Observation c86b2ae5-eadd-447f-90d5-0b6e114aa655 · outbound

This paper cites PLATO: Planning with LLMs and Affordances for Tool Manipulation.

VLMgineer: Vision Language Models as Robotic Toolsmiths PLATO: Planning with LLMs and Affordances for Tool Manipulation

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T16:48:59.496536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:48:59.496536Z digest=sha256:615c7896c46d838d6195d813574a24cd879da5e968d18fd70bfa91d0a8119b2d

Observation b0f1d743-2aa0-4c74-935a-245e6de6c576 · outbound

This paper cites Bimanual dexterity for complex tasks,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Bimanual dexterity for complex tasks,

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T16:48:59.618863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:48:59.618863Z digest=sha256:63186cfe5b5976672b1dfdf98b8536cc2791765c07e284ce37d9273e5b432c79

Observation 21cfa20a-d9f0-4b05-8c8b-cf244f17a165 · outbound

This paper cites Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation.

VLMgineer: Vision Language Models as Robotic Toolsmiths Vegetable Peeling: A Case Study in Constrained Dexterous Manipulation

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T16:48:59.721796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:48:59.721796Z digest=sha256:b4614396b16bd9a4909570347bc0199268f8c1c0c0be2a959da3a17196530431

Observation 95a92f59-0f4f-49cc-9247-4211e82f381d · outbound

This paper cites Language to Rewards for Robotic Skill Synthesis.

VLMgineer: Vision Language Models as Robotic Toolsmiths Language to Rewards for Robotic Skill Synthesis

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T16:48:59.846352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:48:59.846352Z digest=sha256:80017483364fd702961469785209aba07cfd3971a315c3608f462e53143869b9

Observation 846a8b07-91db-45a5-9c97-6f6a7c527485 · outbound

This paper cites Eureka: Human-Level Reward Design via Coding Large Language Models.

VLMgineer: Vision Language Models as Robotic Toolsmiths Eureka: Human-Level Reward Design via Coding Large Language Models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:00.033228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:00.033228Z digest=sha256:ed60d31083ae9a0ce5021d61319bb74364e5188e7630a0c8eab4713d7d217f75

Observation d688ebd5-913a-4ca0-90dd-fa5d0f35500c · outbound

This paper cites Blenderalchemy: Editing 3d graphics with vision-language models,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Blenderalchemy: Editing 3d graphics with vision-language models,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:00.170354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:00.170354Z digest=sha256:782a68b8bb8495bf045e7b1592884b772514f9133f9a038fdb8c6f88614491a3

Observation 33e0b914-87e9-4a4c-88b1-447ccbe3cc2c · outbound

This paper cites Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model.

VLMgineer: Vision Language Models as Robotic Toolsmiths Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:00.339714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:00.339714Z digest=sha256:41117b95420baead9607e0cbdaf6285d6b1347e693991eaa338e99cead84a1bb

Observation 2a32344d-d023-48c0-99d0-5eb025a1b20c · outbound

This paper cites Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset.

VLMgineer: Vision Language Models as Robotic Toolsmiths Blox-Net: Generative Design-for-Robot-Assembly Using VLM Supervision, Physics Simulation, and a Robot with Reset

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:00.491052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:00.491052Z digest=sha256:f167caf133600a4989c799b556d81ab6ac07db46bafd2be7fea478ea2faae00d

Observation 3ca1d378-505f-4424-a8bd-b44b67eaeea5 · outbound

This paper cites Mathematical discoveries from program search with large language models,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Mathematical discoveries from program search with large language models,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:00.628303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:00.628303Z digest=sha256:1ed1931ac496c6848f20e680c4f1335d80438c998127cf2d21e012912dd8abb4

Observation 1e095913-4d3e-417b-b37c-b961a6ae419e · outbound

This paper cites FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch.

VLMgineer: Vision Language Models as Robotic Toolsmiths FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:00.742479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:00.742479Z digest=sha256:c00a30f168bba8b55ed6520a1273958b212aa884e456ae7a7746a0b59f092f88

Observation c4e1853d-31a0-4eaf-a524-d4c04e600dac · outbound

This paper cites Alphaevolve: A gemini-powered coding agent for designing advanced algorithms,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Alphaevolve: A gemini-powered coding agent for designing advanced algorithms,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:00.839779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:00.839779Z digest=sha256:408424d9ab02d51460c80dc56f3eb6c2551e499b0c5d689892ca926f8114dea0

Observation 5abceab4-d58e-45a1-829d-c79b4f9367be · outbound

This paper cites Physical Design using Differentiable Learned Simulators.

VLMgineer: Vision Language Models as Robotic Toolsmiths Physical Design using Differentiable Learned Simulators

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:00.986356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:00.986356Z digest=sha256:f32c3dfe5de852d75bee4b1f365e8282091f039a05db2c2ea2aad425d1167ed0

Observation 625927cd-87f9-4b7b-a93a-fa705f0437c6 · outbound

This paper cites Learning to design and construct bridge without blueprint,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning to design and construct bridge without blueprint,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:01.085239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:01.085239Z digest=sha256:298aff1a1222e16e4e1073028cd867f1922a8c5769342022dc2796a80e2e7781

Observation 9ba0ea76-2e2e-4634-8ae0-edd32f3f29d2 · outbound

This paper cites Learning to design 3d printable adaptations on everyday objects for robot manipulation,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning to design 3d printable adaptations on everyday objects for robot manipulation,

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:01.229970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:01.229970Z digest=sha256:dd6aaf611cb6a69bbb48d55de021365a4f860d42eccb0b2874247d24a4c9c41d

Observation c8a5b814-58cd-4bb0-9bf3-ab957fbd5a36 · outbound

This paper cites Morph: Design co- optimization with reinforcement learning via a differ- entiable hardware model proxy,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Morph: Design co- optimization with reinforcement learning via a differ- entiable hardware model proxy,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:01.385477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:01.385477Z digest=sha256:88e890ff351575a32ccd0050b83d02583c93ef0553bfca6e8dbfc7f6e9870a09

Observation 9b0be4c0-0b15-465e-a490-abfeb4f8d2e6 · outbound

This paper cites Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis.

VLMgineer: Vision Language Models as Robotic Toolsmiths Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis

Reference 18

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:49:14.160816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:01.512809Z digest=sha256:42b25487a754fd66353ef50fd6a39c137c895a6513f118955937f03bfbe1daf6

Observation 0b22dcc2-84e7-4ca5-86ff-7733fd97d214 · outbound

This paper cites Fit2Form: 3D generative model for robot gripper form design,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Fit2Form: 3D generative model for robot gripper form design,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:01.662046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:01.662046Z digest=sha256:b34a97b858e7c28860bd323cf3ba657eca96c12794b4f66e6177d1b0f7b4e34c

Observation 10109b48-ea89-4ab7-a0b2-e9cda17b8de2 · outbound

This paper cites Dynamics-Guided Diffusion Model for Sensor-less Robot Manipulator Design.

VLMgineer: Vision Language Models as Robotic Toolsmiths Dynamics-Guided Diffusion Model for Sensor-less Robot Manipulator Design

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:01.780755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:01.780755Z digest=sha256:d7aa1f7acf68c8d0b68b01a3601ae0aac86f02c22474f8c7f67a47c6006ed316

Observation f294d3a1-fd90-4504-8f42-2e889e8eeab0 · outbound

This paper cites Paperbot: Learning to design real-world tools using paper,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Paperbot: Learning to design real-world tools using paper,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:01.914896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:01.914896Z digest=sha256:7ab8ad892bd098eb46abd8fa75ab4240b0ed3e400897e667aadf7f81e6957aaf

Observation e5091c00-b6df-418c-9f6b-9b4f9941706b · outbound

This paper cites Learning tool morphology for contact-rich manipulation tasks with differentiable simulation,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning tool morphology for contact-rich manipulation tasks with differentiable simulation,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:02.087359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:02.087359Z digest=sha256:54b567b41131175aa7c04fb121a265a10e6b496ba8a00236e03e3906ab367a5a

Observation 8c5a3bb9-a624-4a92-905e-30639449e40a · outbound

This paper cites Lamarckian evolution of simulated modular robots,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Lamarckian evolution of simulated modular robots,

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:02.229041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:02.229041Z digest=sha256:be01cd5f9d83e50fb256b92b34817511fe28db1b2ebdb4d62c3d251c6a1221db

Observation 88d50946-f6c1-4b97-bc36-12d53ceb0f1e · outbound

This paper cites Task-Agnostic Morphology Evolution.

VLMgineer: Vision Language Models as Robotic Toolsmiths Task-Agnostic Morphology Evolution

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:02.379268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:02.379268Z digest=sha256:55a733b9746fb84a6657fc300d1b34cee2b6d4d7ea04703a93cd2e97fb7bbcba

Observation 01a2e9be-94fb-4e75-aa0e-2117de8655a3 · outbound

This paper cites Evolution of morphology through sculpting in a voxel based robot,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Evolution of morphology through sculpting in a voxel based robot,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:02.508399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:02.508399Z digest=sha256:84aa628f6cc374fecab48ea84ba9661f23de86979570ed1d4d6b5d3cefb124c6

Observation 56faf17b-c761-4b31-a3cc-12ae38019318 · outbound

This paper cites Evolving virtual creatures,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Evolving virtual creatures,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:02.619008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:02.619008Z digest=sha256:fe25186c3b55821438e49f73502278ea0dfc1729428cc86cfdce1fa47b989b1d

Observation 47f66f34-09cc-4334-889f-2fb4a0c3bd91 · outbound

This paper cites Symmetry-Aware Robot Design with Structured Subgroups.

VLMgineer: Vision Language Models as Robotic Toolsmiths Symmetry-Aware Robot Design with Structured Subgroups

Reference 27

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:49:13.911648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:02.783877Z digest=sha256:6f274285e9f0c828647682ca729e928ddc07af2be3f98df01305d0cc4ec64c2e

Observation e34e82dc-c3fe-476a-8887-55d8fd4ec8ce · outbound

This paper cites Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design.

VLMgineer: Vision Language Models as Robotic Toolsmiths Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:02.873234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:02.873234Z digest=sha256:16bab2be32663253662d77f0b3607aa4b5d88cb810b641032dd94c7cd3bfac5b

Observation b66479b7-cae7-45ee-8136-17e608a0146d · outbound

This paper cites Task-specific design optimization and fabrication for inflated-beam soft robots with growable discrete joints,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Task-specific design optimization and fabrication for inflated-beam soft robots with growable discrete joints,

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:03.026066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:03.026066Z digest=sha256:0cd5adc863a24b8d933693338db1d87328860c423a5380aa02a74f942f0d9c0b

Observation 5fb005a5-3706-4d91-bedc-9951c880ef12 · outbound

This paper cites Robogrammar: graph grammar for terrain-optimized robot design,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Robogrammar: graph grammar for terrain-optimized robot design,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:03.168775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:03.168775Z digest=sha256:1d15dbdc0b4c0de7e2724315435566f6bb85a89d1b434d0c2b969e5628be4c3c

Observation e54db5be-91f5-4959-b441-151b79805f53 · outbound

This paper cites Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight.

VLMgineer: Vision Language Models as Robotic Toolsmiths Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:03.294927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:03.294927Z digest=sha256:f255a8165457493f5cc18b3a6780fbb3f575865adef974a91e0e5f1c3fa413c3

Observation 46e6e215-dd7d-4386-a743-f9caf2a24451 · outbound

This paper cites Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:03.427367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:03.427367Z digest=sha256:58ee1b915a5e4b115dc3ba3d0f337f592c98e5cb1562a1db56bd4e961bf9e8eb

Observation f51581e7-a4c6-4f7e-896f-2aa584e5edab · outbound

This paper cites Forward Prediction for Physical Reasoning.

VLMgineer: Vision Language Models as Robotic Toolsmiths Forward Prediction for Physical Reasoning

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:03.558507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:03.558507Z digest=sha256:e9114341d797af8f7ea171d3ab6e51c83e466044acb52655ad191b0ca9212fa0

Observation f6daa2df-c025-4c61-be63-e0e8250c03f1 · outbound

This paper cites DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools.

VLMgineer: Vision Language Models as Robotic Toolsmiths DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:03.681853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:03.681853Z digest=sha256:1a259080707a08a88a096e076d02ffa085d36baff1e2de8cdbdd7a46db88de2d

Observation b3042ff0-4c01-49f9-830e-71007598ab5f · outbound

This paper cites Planning with spatial- temporal abstraction from point clouds for deformable object manipulation,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Planning with spatial- temporal abstraction from point clouds for deformable object manipulation,

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:03.783473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:03.783473Z digest=sha256:4a63a2cdd1f69c8f060485ab8b60be75d065978dee77d2215a8dc35dea3257e2

Observation d77f6d88-6d16-4d21-9780-005737556023 · outbound

This paper cites Learning task-oriented grasping for tool manipulation from simulated self-supervision,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning task-oriented grasping for tool manipulation from simulated self-supervision,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:03.923649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:03.923649Z digest=sha256:187c0433efc51edca288306db13c0ee1b06bd1bdd4b95d338b662b525232bf7b

Observation f523a4ce-daa5-41fe-bcf3-f79d75c7c377 · outbound

This paper cites Keto: Learning keypoint representations for tool ma- nipulation,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Keto: Learning keypoint representations for tool ma- nipulation,

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:27.593280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:04.023723Z digest=sha256:855894264b8c3aa792a13779c3178b16955b25890d1abdc47c0112b88ce71a31

Observation 6395eba7-fa16-4cb8-be1d-7f0409b72435 · outbound

This paper cites A causal approach to tool affordance learning,.

VLMgineer: Vision Language Models as Robotic Toolsmiths A causal approach to tool affordance learning,

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:27.334945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:04.131358Z digest=sha256:b88e9122395107bc40a5d86ac16c3684fbe250aba7ada5f84aa68fdae44c98f6

Observation 7968018e-a477-4690-8eac-896d19226eb3 · outbound

This paper cites Deep affordance foresight: Planning through what can be done in the future,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Deep affordance foresight: Planning through what can be done in the future,

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:27.026235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:04.265866Z digest=sha256:3cfcb5cc45327f3ab5055ef3d281d4361b57166b887bc4e75c47c5e0d7f12fe3

Observation d021d732-6470-46f0-8dab-8ae9c29fe719 · outbound

This paper cites Tool as Embodiment for Recursive Manipulation.

VLMgineer: Vision Language Models as Robotic Toolsmiths Tool as Embodiment for Recursive Manipulation

Reference 40

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:49:13.487084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:04.411949Z digest=sha256:05b6e9f13cba9d515658ef072304e4416d24c822d8621dcc6987e408b1a595f3

Observation 61bf62f1-a928-4f4f-aefd-254f647172b8 · outbound

This paper cites Creative robot tool use with large language models,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Creative robot tool use with large language models,

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:26.781511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:04.537641Z digest=sha256:8898fc875cb803695ca28b46c1a3af6fcf511a5d0d2033a291a7be7995cf0d64

Observation b4746fca-64ef-4c24-8a09-b9c2fe636663 · outbound

This paper cites Differentiable physics and stable modes for tool-use and manipulation planning,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Differentiable physics and stable modes for tool-use and manipulation planning,

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:26.527024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:04.690264Z digest=sha256:aac0747dc22976abe09c6795e24a8bfda8bcda713f9b8a06ac4355c450b08e06

Observation 52337678-843c-4dbf-b0a4-b679167929a3 · outbound

This paper cites Co-optimizing robot, environment, and tool design via joint manipulation planning,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Co-optimizing robot, environment, and tool design via joint manipulation planning,

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:26.273795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:04.799447Z digest=sha256:286de25e4c525afe5fe08708935972aa3b640b622beaf95debe18232e1966d04

Observation c64e5e3b-4dc5-4dc3-8d77-89fcf7f14e5c · outbound

This paper cites Curriculum-based co-design of morphology and control of voxel-based soft robots,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Curriculum-based co-design of morphology and control of voxel-based soft robots,

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:26.051938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:04.914548Z digest=sha256:579f721701390811feb02c6de4a36b91cf41b33d78eef012894bd5effdce3cbe

Observation 403acb33-2e97-438e-95e3-58e2d73614e5 · outbound

This paper cites Preco: Enhancing generalization in co- design of modular soft robots via brain-body pre-training,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Preco: Enhancing generalization in co- design of modular soft robots via brain-body pre-training,

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:25.550350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:05.168283Z digest=sha256:ec2c9c9fa87a5efcabb187d61755825103360477e2b5c68fca21fa1a3abc95fb

Observation f6f3b34e-ad3b-4ab5-9f2a-a5dab5d6982b · outbound

This paper cites Data- efficient co-adaptation of morphology and behaviour with deep reinforcement learning,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Data- efficient co-adaptation of morphology and behaviour with deep reinforcement learning,

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:25.311675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:05.361889Z digest=sha256:52185bffd2106407db8aa26057ef5632be8cfbfcfb33eb0a572dbab2ff6db500

Observation 22976eca-7f85-4581-b8e6-a5df29a29373 · outbound

This paper cites Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design.

VLMgineer: Vision Language Models as Robotic Toolsmiths Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:05.478378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:05.478378Z digest=sha256:965418afb2e0a4120a3a2c5457176da74b7fa38ed52bf5b8790164cec0cfb3d0

Observation 044918d7-e6fb-4c3b-9410-384a9c11d712 · outbound

This paper cites Learning-in-the-loop optimization: End-to-end control and co-design of soft robots through learned deep latent representations,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning-in-the-loop optimization: End-to-end control and co-design of soft robots through learned deep latent representations,

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:24.997689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:05.580101Z digest=sha256:3fef1898204fd68f6ef0785f63b03c3cb58237ea4c5caba6415b44106d915e39

Observation 0947eed4-fb6b-4a76-9e68-44c2cf65b77c · outbound

This paper cites Scalable co-optimization of morphology and control in embodied machines,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Scalable co-optimization of morphology and control in embodied machines,

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:24.689316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:05.674550Z digest=sha256:7cde015219535c59c9eb995aee1846b5e3e3767bae34a69c5d41baadc74a5903

Observation 204277f2-3557-4101-b776-45862fde1f5e · outbound

This paper cites Investigating Premature Convergence in Co-optimization of Morphology and Control in Evolved Virtual Soft Robots.

VLMgineer: Vision Language Models as Robotic Toolsmiths Investigating Premature Convergence in Co-optimization of Morphology and Control in Evolved Virtual Soft Robots

Reference 50

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:49:13.266611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:05.758702Z digest=sha256:59b5f74ad0cea745d41b99acefc9b67f70941d5dd897f01aecd4c322b1b06ed0

Observation 10974d44-aeb7-4546-85fc-9ecf662256da · outbound

This paper cites Text2Robot: Evolutionary Robot Design from Text Descriptions.

VLMgineer: Vision Language Models as Robotic Toolsmiths Text2Robot: Evolutionary Robot Design from Text Descriptions

Reference 51

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:49:13.028035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:05.865537Z digest=sha256:58949483597466c6d919ebb9f2b587b555a5e0eb7583df6f2777ef829d0237fc

Observation e3dbffee-198e-4d88-b773-296ed31a75b7 · outbound

This paper cites Data-efficient learning of morphology and controller for a microrobot,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Data-efficient learning of morphology and controller for a microrobot,

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:24.455401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:05.968965Z digest=sha256:c7ee8a33ac73ca26a6d56fd211ae162bcf746a1c00a7fc328c620687966e3240

Observation 2fc4a558-2761-4e45-8520-bd72fdb011c8 · outbound

This paper cites Jointly learning to construct and control agents using deep reinforcement learning,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Jointly learning to construct and control agents using deep reinforcement learning,

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:24.174562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:06.052312Z digest=sha256:ebf76df9003eb19bf579cdb3570faa1aefe39f87628141a4af135085c7079735

Observation c605db0d-f5dd-40f8-a665-2b61aa5c1ae6 · outbound

This paper cites Reinforcement learning for improving agent design,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Reinforcement learning for improving agent design,

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:23.921908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:06.174676Z digest=sha256:82eec4e8ec504624afb7a0b6d1ba4963704455e5693ab026cd7b9e87147bc3f9

Observation 54d87ad4-fc22-4b81-b967-e9acf68a2607 · outbound

This paper cites Evolution gym: A large-scale benchmark for evolving soft robots,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Evolution gym: A large-scale benchmark for evolving soft robots,

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:23.599392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:06.300675Z digest=sha256:54d32e3ec8702d25318c681e6e3459169a05c85390b4823316599ba80410f623

Observation 324a1344-4c59-43cf-b88a-dd798633d18b · outbound

This paper cites Learning to control self-assembling morphologies: a study of generalization via modularity,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning to control self-assembling morphologies: a study of generalization via modularity,

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:23.336408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:06.466831Z digest=sha256:3c1bc3cd78ef22e7980af22beecdcbd050ff48e17a0807011cdef40ab3c97469

Observation f7fe9dd4-b8e4-423e-b55f-0131f5af2c41 · outbound

This paper cites Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning.

VLMgineer: Vision Language Models as Robotic Toolsmiths Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning

Reference 57

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:49:12.781832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:06.567709Z digest=sha256:3ab333b2f9a7091ca65d27f718658c370de62bcb1e8b5f91f3b70ede43f80038

Observation df00f0ad-600b-4ac7-aad0-8f37f3e2e406 · outbound

This paper cites Learning to Design and Use Tools for Robotic Manipulation.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning to Design and Use Tools for Robotic Manipulation

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:06.690179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:06.690179Z digest=sha256:a820d7215efaf3bbdc94d91d9b5812948e1067f76a060668d29a71d63be83a6b

Observation 4badcd13-6519-4792-8b94-5fb37efe6079 · outbound

This paper cites An end-to-end differentiable framework for contact-aware robot design,.

VLMgineer: Vision Language Models as Robotic Toolsmiths An end-to-end differentiable framework for contact-aware robot design,

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:06.813108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:06.813108Z digest=sha256:328bcb2e9e0ac671519118e0d87b37d54b09c45ef1defa0294dc8e11686557cf

Observation 426f1353-7cc4-47e1-acb9-5c5b51e69f19 · outbound

This paper cites Tool shape optimization through backpropagation of neural network,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Tool shape optimization through backpropagation of neural network,

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:23.074508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:06.962058Z digest=sha256:01a5087e7fecbd1dce35c82f849950d5ddbd266f9c82a314ab41b1d5d694b454

Observation f5de6a4d-89df-43eb-9549-fad8b7e9a63c · outbound

This paper cites Robomorph: Evolving robot morphology using large language models,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Robomorph: Evolving robot morphology using large language models,

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:07.097477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:07.097477Z digest=sha256:fcfb7b7a38b8cfa492466eccac287ed6c9211b2ce95b27fdde97d6b9aafab31f

Observation 38429a61-bef4-4936-9ebe-22758aeeb4bc · outbound

This paper cites Large language models as natural selector for embodied soft robot design,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Large language models as natural selector for embodied soft robot design,

Reference 62

Resolution
verified exact
raw_fallback, observed 2026-08-06T16:49:12.436796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:07.245686Z digest=sha256:b6cce5b5015652acca878fbdaa33c606c185e1efe212fdf087828ad0ace9fdc1

Observation fd927a07-c1d4-4236-97d7-ca12e02870ca · outbound

This paper cites Laser: Towards diversified and generalizable robot design with large language models,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Laser: Towards diversified and generalizable robot design with large language models,

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:22.833893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:07.363438Z digest=sha256:0a5d3edbafa68b109d0c622c11a0e15386f1d5b54a57ba4e5d0308b3b2cca970

Observation 362badf0-b07c-45cc-89ed-d292beb2e00c · outbound

This paper cites an unresolved cited work.

VLMgineer: Vision Language Models as Robotic Toolsmiths Unresolved cited work

Reference 64

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:49:22.529813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:07.456825Z digest=sha256:2563e5df19f03486d37719843d3290b4ea38475535de02cf714c2448fbd3ff50

Observation d78b8be0-03d2-46fd-bd9c-f11921d26831 · outbound

This paper cites Evolutionary robotics: what, why, and where to,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Evolutionary robotics: what, why, and where to,

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:22.197998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:07.558592Z digest=sha256:a4dae223b5ff6d554feb01d92e2bdbc352db678c37f29f67e985ce48938d55db

Observation 356814a6-2256-4d55-a1b9-cf93afc43e83 · outbound

This paper cites Tool Macgyvering: A Novel Framework for Combining Tool Substitution and Construction.

VLMgineer: Vision Language Models as Robotic Toolsmiths Tool Macgyvering: A Novel Framework for Combining Tool Substitution and Construction

Reference 66

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:49:12.038788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:07.701594Z digest=sha256:a6896c70eddb3260ea344f18908837d23ac62d3654ef00ee2cd2d52265edaa1d

Observation 16b824e1-624f-4183-8ebc-087e70412a56 · outbound

This paper cites Learning Robotic Assembly from CAD.

VLMgineer: Vision Language Models as Robotic Toolsmiths Learning Robotic Assembly from CAD

Reference 67

Resolution
verified exact
local_arxiv, observed 2026-08-06T16:49:11.715824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:07.791653Z digest=sha256:f4cf310c32d3da135111af7150ec464c57e371ab1a24d6fb8125976142babe73

Observation a2b33b16-3a01-4f3f-a0a8-9f613e9f3d0f · outbound

This paper cites Keypoint action tokens enable in-context imitation learning in robotics,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Keypoint action tokens enable in-context imitation learning in robotics,

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:21.901229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:07.895385Z digest=sha256:21430350d11b5e40dd727faba981de687cc222b2c182c4097e7a01ca5f84e0a8

Observation ba32f05d-1ba0-4b6d-abab-9de6bc78abff · outbound

This paper cites In-context learning enables robot action prediction in llms,.

VLMgineer: Vision Language Models as Robotic Toolsmiths In-context learning enables robot action prediction in llms,

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:21.614330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:08.033898Z digest=sha256:834c72e3ce9c5af2002ceeb622e5f5aaa4ec1e2fa86634ac656e57820c04b7bf

Observation bc382377-857b-47a5-a3bb-d104da713798 · outbound

This paper cites Rlbench: The robot learning benchmark & learning environment,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Rlbench: The robot learning benchmark & learning environment,

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:21.351590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:08.153931Z digest=sha256:d4aaf62cb7ea170d4c87bf808ae4f04683a914c70dccd3bf06b9168b2eb2f426

Observation 5af18f38-a063-456f-b883-b0fb6b0af3c8 · outbound

This paper cites A novel tool-use mode in animals: New caledonian crows insert tools to transport objects,.

VLMgineer: Vision Language Models as Robotic Toolsmiths A novel tool-use mode in animals: New caledonian crows insert tools to transport objects,

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:21.112900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:08.277049Z digest=sha256:a0e8daa3ab1ff197a686b8561b68d90c94ffe379a61b32ed812b9a19b94103af

Observation 98220187-89e6-4f42-bcd2-ba3323e85d72 · outbound

This paper cites Pybullet gymperium,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Pybullet gymperium,

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:20.883748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:08.415993Z digest=sha256:d411e9f55c8238bdc13aaca0c2ce594f3fa43b1bfcdcacb56e0f18ee42d067f2

Observation c73bf97e-230a-4c92-973f-5734b2952ec7 · outbound

This paper cites SAPIEN: A simulated part-based interactive environment,.

VLMgineer: Vision Language Models as Robotic Toolsmiths SAPIEN: A simulated part-based interactive environment,

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:20.648599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:08.537676Z digest=sha256:9c5cf1d222631ce1ad8932fcf5f556356f4b1c97dbf3628d72c9ec8a9a241855

Observation eca33180-45de-48c2-8612-84ce63720c52 · outbound

This paper cites Benchmarking in manipulation re- search: Using the Yale-CMU-Berkeley object and model set,.

VLMgineer: Vision Language Models as Robotic Toolsmiths Benchmarking in manipulation re- search: Using the Yale-CMU-Berkeley object and model set,

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:20.397139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:08.601274Z digest=sha256:ca2e10e355163e201d6e08cfe28eabdca4bf230c364d7382da5bc5909d6e5879

Observation 914a5390-5546-4116-a704-24b43d785c39 · outbound

This paper cites Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning.

VLMgineer: Vision Language Models as Robotic Toolsmiths Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-06T16:49:08.722732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:49:08.722732Z digest=sha256:da18749f1b5f0498867f0b3c161888617525804abb608f606ab486c3fc79baa0

Observation 43ac7e9d-67c6-4c4a-aadd-c71befc067a1 · outbound

This paper cites (ii) Participants then had five minutes to write a prompt in English specifying their desired tool design and robot action.

VLMgineer: Vision Language Models as Robotic Toolsmiths (ii) Participants then had five minutes to write a prompt in English specifying their desired tool design and robot action

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:20.106659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:08.801231Z digest=sha256:d5b632cdf909f1fc592233b979c64eb108cffdb31b6ff44f554e69722d2d5400

Observation 91d6a3f1-d575-4415-9450-e52af209d453 · outbound

This paper cites an unresolved cited work.

VLMgineer: Vision Language Models as Robotic Toolsmiths Unresolved cited work

Reference 78

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:49:19.857108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:08.876346Z digest=sha256:b95800518163169dd4ff0b15c1b78aabf99c10ddfb0aa26ea699b18accf07c85

Observation a2b685e7-90e3-4597-9d0e-c608da695210 · outbound

This paper cites distance-to-exit.

VLMgineer: Vision Language Models as Robotic Toolsmiths distance-to-exit

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:19.597277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:09.039619Z digest=sha256:550ac3f93ee9df9ef75f68f87c4959775e63902add7a343964c0dc7a95312b94

Observation a641f0b2-c75c-496f-bf86-3466350b80a6 · outbound

This paper cites The design agent is provided with task context as illustrated in Fig.

VLMgineer: Vision Language Models as Robotic Toolsmiths The design agent is provided with task context as illustrated in Fig

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:19.362273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:09.100504Z digest=sha256:0e937c23a945807cc2d3cd6e43da7a8814bdb21e069b42929a11834d5a3fb6a8

Observation 45aed25e-4f59-420d-ba82-0a454e170b37 · outbound

This paper cites For each agent, we prompt it to generate ntool number of tool designs, and naction number of action waypoint samples that correspond to each tool design.

VLMgineer: Vision Language Models as Robotic Toolsmiths For each agent, we prompt it to generate ntool number of tool designs, and naction number of action waypoint samples that correspond to each tool design

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:19.067976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:09.159826Z digest=sha256:ace382fed1b28ef5f529df08a48531d73b8c366e92c47301e77a7024331aef31

Observation 02ffad2b-aa47-4bce-a01b-0c2bd4c0da04 · outbound

This paper cites virtual joint.

VLMgineer: Vision Language Models as Robotic Toolsmiths virtual joint

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:18.806904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:09.292009Z digest=sha256:c6d3f34ccd04ed342408e74fe9f4572c7a62f8a2baa26931728b637544b0e515

Observation 64bab6c8-38b3-4762-bfa3-f5acf6cd6ec2 · outbound

This paper cites an unresolved cited work.

VLMgineer: Vision Language Models as Robotic Toolsmiths Unresolved cited work

Reference 83

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:49:18.568007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:09.421705Z digest=sha256:7a1194c0cc0e58147043672e2081072f59f8a820280344c7bca0af5a915c966f

Observation dfa9d619-b907-42bf-891b-aa7dfee225f8 · outbound

This paper cites evolution mission introduction prompt.

VLMgineer: Vision Language Models as Robotic Toolsmiths evolution mission introduction prompt

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:18.274399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:09.563220Z digest=sha256:89a50a3e446173bf9decc1deef006a84ac901adc4220eb6ee0f2edf2df90139d

Observation b98b655c-6e2d-4a84-b895-f5f81b1053ae · outbound

This paper cites an unresolved cited work.

VLMgineer: Vision Language Models as Robotic Toolsmiths Unresolved cited work

Reference 85

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:49:17.999949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:09.686796Z digest=sha256:894459cbedea5c2ca8bc723032e72560b9a756873a93eae450370b96bcb51097

Observation 1f9631ce-e40e-40dd-b88c-987a656737ac · outbound

This paper cites Evolutionary Process.

VLMgineer: Vision Language Models as Robotic Toolsmiths Evolutionary Process

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:17.674245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:09.881972Z digest=sha256:34124cfc2cef977a1f6071ed7fa42c3115dce7904ffa1d8db309470ee5d31a3d

Observation 49091bee-0e58-4d75-a2a9-bc697ed3dee4 · outbound

This paper cites an unresolved cited work.

VLMgineer: Vision Language Models as Robotic Toolsmiths Unresolved cited work

Reference 87

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:49:17.404147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:10.002181Z digest=sha256:9347e3e8831400b5cb3b5f06da99653690cc5378391f4e9baef3728ea9a07a94

Observation d0dc1e75-cc61-4615-ae5e-5b5fe2f27d6f · outbound

This paper cites an unresolved cited work.

VLMgineer: Vision Language Models as Robotic Toolsmiths Unresolved cited work

Reference 88

Resolution
unresolved
raw_fallback, observed 2026-08-06T16:49:17.088656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:10.129690Z digest=sha256:e6685e38ec484621e16fd0475846525c4847889278e40de8a8f774f6c9cef571

Observation c9050439-928b-48d9-9841-9e64b46e0b8f · outbound

This paper cites Write down the spatial relationship, including by not limited to the position, orientation, dimension, and geometry of all the objects in the scene.

VLMgineer: Vision Language Models as Robotic Toolsmiths Write down the spatial relationship, including by not limited to the position, orientation, dimension, and geometry of all the objects in the scene

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:16.836125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:10.248561Z digest=sha256:9a9598f1d4904f18bd5e8f6780df77e509edbd8b08e605d6579974837b8b911b

Observation b081c908-a68b-455f-b4ce-dc6f0c956934 · outbound

This paper cites Tool Specification.

VLMgineer: Vision Language Models as Robotic Toolsmiths Tool Specification

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:16.569212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:10.378396Z digest=sha256:e431c1fe849cd940abacc764e7bf26858409a049b95c9adbca09d1dc44b85ff1

Observation 723baa9c-8fc4-4c86-93b6-acbb74b91284 · outbound

This paper cites panda_virtual.

VLMgineer: Vision Language Models as Robotic Toolsmiths panda_virtual

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:16.278517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:10.480554Z digest=sha256:647a410bea89b38d6baaa541e5fe82c5083ca34daad92eb0feb9834900bdbef3

Observation 673441b1-7038-4e8a-a045-1952ad080f92 · outbound

This paper cites panda_virtual.

VLMgineer: Vision Language Models as Robotic Toolsmiths panda_virtual

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:16.006208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:10.635928Z digest=sha256:28240611695fc5a66919fea99d5b048d9245d40e9b0edb60ad5c0466efc5ab7f

Observation 78a17703-189f-4470-a775-71e14533e9de · outbound

This paper cites action set.

VLMgineer: Vision Language Models as Robotic Toolsmiths action set

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:15.728226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:10.826785Z digest=sha256:3b450c4893c2495cf677d2b97222ca5ae1573667c0dade31f68ae8742155041c

Observation 0299c7bf-6df7-4b87-a462-8d4222b2bebd · outbound

This paper cites Negative x: Towards the back of the table.

VLMgineer: Vision Language Models as Robotic Toolsmiths Negative x: Towards the back of the table

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:15.507964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:10.912853Z digest=sha256:4f51c2b853a23777d4e356ea1533030c8c703f41dc0c45900edd23e18348e8ed

Observation 84b99411-d987-43c0-ae92-c1a868788b86 · outbound

This paper cites For each of the ntool tool designs, you can choose to either mutate or crossover.

VLMgineer: Vision Language Models as Robotic Toolsmiths For each of the ntool tool designs, you can choose to either mutate or crossover

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:15.252606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:11.031635Z digest=sha256:e92351caad86ac820a5ef3c2d254b80ac795a870386729c6f2ee38ea5e203fc1

Observation 3da68d78-57c6-4be8-adf6-52c106fe916b · outbound

This paper cites You operate with boldness and brilliance in the physical realm.

VLMgineer: Vision Language Models as Robotic Toolsmiths You operate with boldness and brilliance in the physical realm

Reference 96

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:15.002788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:11.155599Z digest=sha256:6ef304e767a6465647bbf8cc87ae165075e92cfaf757521cda64fd327aa97216

Observation 129e11db-f3b9-46a3-a0f1-d0cdfdc30d80 · outbound

This paper cites You have a robot arm that sits in the origin of your environment.

VLMgineer: Vision Language Models as Robotic Toolsmiths You have a robot arm that sits in the origin of your environment

Reference 97

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:14.757027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:11.311621Z digest=sha256:ebe70f719efb912bb4c5e61cde2df07d78f0fb66ac13cfe1c5d4574903ae3595

Observation bf37ed33-f3a4-4823-8bbe-ec74e04baa6c · outbound

This paper cites Royalty Free No Ai License.

VLMgineer: Vision Language Models as Robotic Toolsmiths Royalty Free No Ai License

Reference 98

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:14.516607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:11.453392Z digest=sha256:f66bb53a40412725d6e51cedbf59f5f68c58dbb9cbd83f0b48427294df29278d

Observation 7f73dd0c-b826-42e3-8385-32ae6407c214 · outbound

This paper cites Available: https://openreview.net/forum? id=r9fX833CsuN.

VLMgineer: Vision Language Models as Robotic Toolsmiths Available: https://openreview.net/forum? id=r9fX833CsuN

Reference 2023

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T16:49:25.805017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-06T16:49:05.034241Z digest=sha256:5dba2d53d7c835e82cf163d1d458004dcc219f57af0276a8853f361c3bd73567

Pith citing papers

Observation 5a36d9d1-4eca-4cc6-9fab-553fe9e60cac · inbound

Debate2Create: Robot Co-design via Multi-Agent LLM Debate cites this paper.

Debate2Create: Robot Co-design via Multi-Agent LLM Debate VLMgineer: Vision Language Models as Robotic Toolsmiths

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-04T07:27:03.967235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T07:27:03.967235Z digest=sha256:c7adf75c0a70e8340355166afbb7ee9b713fa6acea6b3f102027ddc136a17eb0

Observation 8f0d6bff-d428-4b5a-9c29-b87d5974fcf6 · inbound

ESC: Emotional Self-Correction for Reliable Vision-Language Models cites this paper.

ESC: Emotional Self-Correction for Reliable Vision-Language Models VLMgineer: Vision Language Models as Robotic Toolsmiths

Reference 24

Resolution
verified exact
arxiv_id, observed 2026-07-03T21:28:58.450872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-07-03T21:20:00.041277Z digest=sha256:4c77784f1356321e3321e7d07ab7c21cd6f935e18f05667feb6cbcfee9dd3790

Observation 2dfae5bd-642f-44bc-bc84-dbc00add0b77 · inbound

IMBench: A Benchmark for Intuitive Robotic Manipulation cites this paper.

IMBench: A Benchmark for Intuitive Robotic Manipulation VLMgineer: Vision Language Models as Robotic Toolsmiths

Reference 85

Resolution
malformed identifier
no resolver link, observed 2026-08-01T22:45:15.341522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T22:45:15.341522Z digest=sha256:35e3405d28671001d8a8bc776b74e11e4420f05832c23c02187a90f5091f840f