Paper Citation Record · LEDGER

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents

As of 24 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2605.20246.

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

pith.paper-citation-record.v1
2605.20246 v2

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T09:06:03.221498Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+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

31 of 31 outbound references displayed

verified exact22
verified fuzzy8
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 066c5b2e-2e54-4b0f-a100-fbf187bc44b3 · outbound

This paper cites InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:06:18.886667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f291730-6b29-4c24-8038-779259a856a5 · outbound

This paper cites Qwen2.5-vl technical report.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Qwen2.5-vl technical report

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T09:06:20.314370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 67000697-7a1d-43ad-853d-60a644c93873 · outbound

This paper cites Qwen2.5-VL Technical Report.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Qwen2.5-VL Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:06:20.235878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a8bffc09-6934-4936-b0d6-e73e97eb518a · outbound

This paper cites Video pretraining (vpt): Learning to act by watching unlabeled online videos.Advances in Neural Information Processing Systems, 35:24639–24654.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Video pretraining (vpt): Learning to act by watching unlabeled online videos.Advances in Neural Information Processing Systems, 35:24639–24654

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T09:06:20.318146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 23336069-bd0d-4da8-bd94-12e81418c2be · outbound

This paper cites Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.226388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 27697d87-0687-49be-80d8-6a6f8f6acc9a · outbound

This paper cites Freeman, Frédo Durand, Eli Shechtman, and Xun Huang.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Freeman, Frédo Durand, Eli Shechtman, and Xun Huang

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T09:06:18.909678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 23a36722-1d0e-4764-8ccb-ffa826d894d3 · outbound

This paper cites Rocket-1: Mastering open-world interaction with visual-temporal context prompting.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Rocket-1: Mastering open-world interaction with visual-temporal context prompting

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T09:06:20.307643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fe28cfab-1196-4ff2-906d-d4bad9509c0c · outbound

This paper cites Liu, Ram Vasudevan, and Maani Ghaffari.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Liu, Ram Vasudevan, and Maani Ghaffari

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.217335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bb003685-2125-4a27-9b3e-36cd4c61ca87 · outbound

This paper cites Compassnav: Steering from path imitation to decision understanding in navigation.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Compassnav: Steering from path imitation to decision understanding in navigation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T09:06:20.310942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 70b77976-9598-43f0-b8db-aa3ea75dff5b · outbound

This paper cites JARVIS-VLA: Post- training large-scale vision language models to play visual games with keyboards and mouse.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents JARVIS-VLA: Post- training large-scale vision language models to play visual games with keyboards and mouse

Reference 10

Resolution: verified exact; doi, observed 2026-05-22T09:06:18.900244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8221cfde-8f7e-4bef-ba75-c718e1322d5a · outbound

This paper cites Coloragent: Building a robust, personalized, and interactive os agent.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Coloragent: Building a robust, personalized, and interactive os agent

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.207848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fa8e4814-d2a9-4f46-87d5-b9de4ac112fc · outbound

This paper cites Steve-1: A generative model for text-to-behavior in minecraft.Advances in Neural Information Processing Systems, 36:69900–69929.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Steve-1: A generative model for text-to-behavior in minecraft.Advances in Neural Information Processing Systems, 36:69900–69929

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T09:06:20.300899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 76f3ea3e-39cc-41b3-84cc-b3999cb62a63 · outbound

This paper cites MCU: An Evaluation Framework for Open-Ended Game Agents.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents MCU: An Evaluation Framework for Open-Ended Game Agents

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.148998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cc0cdb18-3e2a-4c25-bbde-e8b331d4a0a6 · outbound

This paper cites NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:06:20.198974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ea22657c-6db6-4cc3-b7b7-9da40c8ed92a · outbound

This paper cites Interactive Language: Talking to Robots in Real Time.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Interactive Language: Talking to Robots in Real Time

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.194865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b5aef6f7-a30b-430b-a5ab-7c7f7ad48ee8 · outbound

This paper cites Nitrogen: An open foundation model for generalist gaming agents.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Nitrogen: An open foundation model for generalist gaming agents

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T09:06:20.297001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e5cdfbfa-7241-425a-bd87-39e978b04782 · outbound

This paper cites Nitrogen: An open foundation model for generalist gaming agents.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Nitrogen: An open foundation model for generalist gaming agents

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.190443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fe16d6f4-0897-4cbd-9059-6e05603b89e4 · outbound

This paper cites Gameworld: Towards standardized and verifiable evaluation of multimodal game agents.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Gameworld: Towards standardized and verifiable evaluation of multimodal game agents

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T09:06:20.304168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 48e98a13-db5c-4b6d-92a5-97c9c12688b2 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:06:20.212533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 63a64880-a6fa-41d1-a4d1-6c8ea82ca854 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents HybridFlow: A Flexible and Efficient RLHF Framework

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:06:20.231172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d7c09be8-2028-4ab9-b67d-f3049fe923ed · outbound

This paper cites MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.173865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f59a9f64-b71f-477a-a4e1-eef8872c6b4a · outbound

This paper cites Lumine: An open recipe for building generalist agents in 3d open worlds.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Lumine: An open recipe for building generalist agents in 3d open worlds

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.178376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3a6782f4-b59d-491e-ae6d-c3869e43404a · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:06:20.182452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 318df860-02fc-46be-b865-2464a94a6c03 · outbound

This paper cites Openha: A series of open-source hierarchical agentic models in minecraft.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Openha: A series of open-source hierarchical agentic models in minecraft

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.159090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3394bc5e-ef40-461d-b7c9-7483ed52d96e · outbound

This paper cites Game-tars: Pretrained foundation models for scalable generalist multimodal game agents.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Game-tars: Pretrained foundation models for scalable generalist multimodal game agents

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.164107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bdf00b0d-c6d3-4b39-9db2-1931e3f76182 · outbound

This paper cites Agentgym: Evaluating and training large language model-based agents across diverse environments.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Agentgym: Evaluating and training large language model-based agents across diverse environments

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T09:06:20.293099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d3699671-cc8d-426f-b115-87275d78e961 · outbound

This paper cites Etp-r1: Evolving topological planning with reinforcement fine-tuning for vision-language navigation in continuous environments.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Etp-r1: Evolving topological planning with reinforcement fine-tuning for vision-language navigation in continuous environments

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.154173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 61751152-934b-419a-a5b7-aea962ca45f6 · outbound

This paper cites Agentrl: Scaling agentic reinforcement learning with a multi-turn, multi-task framework.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Agentrl: Scaling agentic reinforcement learning with a multi-turn, multi-task framework

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.168920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f75eb785-be6c-4683-9ee6-de09f904d8bb · outbound

This paper cites Activevln: Towards active exploration via multi-turn rl in vision-and-language navigation.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Activevln: Towards active exploration via multi-turn rl in vision-and-language navigation

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.186483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9c48a5f6-d393-45f8-b7cf-1057e3bbb9da · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:06:20.203515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f510b5a-f0e7-4489-be3b-178361324bbf · outbound

This paper cites mine iron ore.

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents mine iron ore

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:06:20.221332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

No inbound Pith citation observations are available.