ARXIV:2602.16444 · ROBOTIC TASK AUTOMATION · SUBMITTED 17 MAR · 19:46 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsErrorProof: failed

RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

Q: What products could be built from this research?

To productize, RoboGene can be offered as a SaaS solution, where companies subscribe for access to a continuous stream of validated robotic tasks that match their specific environments and robot capabilities.

Q: What are the practical use cases?

RoboGene could be used by robotics companies to provide a steady supply of diverse training tasks for robots, improving their adaptability and functionality in unstructured environments like warehouses or manufacturing plants.

arXiv

Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

Blocked on Code›Score8.0Evidence failed

Opportunity summary

Pain Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

Evidence 0 refs | 0 sources | 33% coverage

Blocker Evidence failed

Open Build Read PDF Signal Canvas Track

PROBLEM

Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application. Unlike data collection from web in vision or language, robotic data collection is an active process incurring prohibitive…

METHOD

Full abstract

The pursuit of general-purpose robotic manipulation is hindered by the scarcity of diverse, real-world interaction data. Unlike data collection from web in vision or language, robotic data collection is an active process incurring prohibitive physical costs. Consequently, automated task curation to maximize data value remains a critical yet under-explored challenge. Existing manual methods are unscalable and biased toward common tasks, while off-the-shelf foundation models often hallucinate physically infeasible instructions. To address this, we introduce RoboGene, an agentic framework designed to automate the generation of diverse, physically plausible manipulation tasks across single-arm, dual-arm, and mobile robots. RoboGene integrates three core components: diversity-driven sampling for broad task coverage, self-reflection mechanisms to enforce physical constraints, and human-in-the-loop refinement for continuous improvement. We conduct extensive quantitative analysis and large-scale real-world experiments, collecting datasets of 18k trajectories and introducing novel metrics to assess task quality, feasibility, and diversity. Results demonstrate that RoboGene significantly outperforms state-of-the-art foundation models (e.g., GPT-4o, Gemini 2.5 Pro). Furthermore, real-world experiments show that VLA models pre-trained with RoboGene achieve higher success rates and superior generalization, underscoring the importance of high-quality task generation. Our project is available at https://robogene-boost-vla.github.io.

RESULT

ScienceToStartup currently rates this 8.0/10 on the public viability pass. Results demonstrate that RoboGene significantly outperforms state-of-the-art foundation models (e.g., GPT-4o, Gemini 2.5 Pro).

WHY NOW

Robotic Task Automation moved forward this cycle; last verified April 2026. Public score 8.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score8.0

PainAutomate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

Evidence0 refs | 0 sources | 33% coverage

Blockermissing authors

Analysis summary

Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsErrorProof: failed

ARXIV:2602.16444 · ROBOTIC TASK AUTOMATION · SUBMITTED 17 MAR · 19:46 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsErrorProof: failed

RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

arXiv

Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

Blocked on Code›Score8.0Evidence failed

Opportunity summary

Pain Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

Evidence 0 refs | 0 sources | 33% coverage

Blocker Evidence failed

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Robotic Task Automation moved forward this cycle; last verified April 2026. Public score 8.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score8.0

PainAutomate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

Evidence0 refs | 0 sources | 33% coverage

Blockermissing authors

Analysis summary

Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsErrorProof: failed

Paper Pack

10.48550/arXiv.2602.16444

RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

failed

0 refs; 0 sources; 33% coverage.

What was readable

linkedon filenot materialized8 extracted50 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

8.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Robotic Task Automation moved forward this cycle; last verified April 2026. Public score 8.0/10.

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
Results demonstrate that RoboGene significantly outperforms state-of-the-art foundation models (e.g., GPT-4o, Gemini 2.5 Pro).
Implicationpartial
Directly stated in abstract with clear comparative language and supported by quantitative analysis mentioned in the analysis.
Verificationpartial
partial
Evidencepartial
To address this, we introduce RoboGene, an agentic framework designed to automate the generation of diverse, physically plausible manipulation tasks across single-arm, dual-arm, and mobile robots.
Implicationpartial
Explicitly stated in abstract as the core capability of the introduced framework.
Verificationpartial
partial
Evidencepartial
Furthermore, real-world experiments show that VLA models pre-trained with RoboGene achieve higher success rates and superior generalization...
Implicationpartial
Directly stated in abstract as a key result, implying a causal link between RoboGene's task generation and improved VLA performance.
Verificationpartial
partial
Evidencepartial
It uses a Least Frequently Used (LFU) strategy to cover under-explored task spaces...
Implicationpartial
Explicitly described in the analysis excerpt as a core component of the method.
Verificationpartial
partial
Evidencepartial
...and a self-reflection mechanism ensures tasks meet physical constraints and novelty demands.
Implicationpartial
Explicitly described in the analysis excerpt as a core component of the method.
Verificationpartial
partial
Evidencepartial
We conduct extensive quantitative analysis and large-scale real-world experiments, collecting datasets of 18k trajectories and introducing novel metrics to assess task quality, feasibility, and diversity.
Implicationpartial
Directly stated in abstract with specific numeric evidence (18k trajectories) and methodological detail.
Verificationpartial
partial
Evidencepartial
The framework may still require significant adaptation for different robotic platforms...
Implicationpartial
Explicitly stated as a caveat in the analysis excerpt, indicating a recognized limitation.
Verificationpartial
partial
Evidencepartial
RoboGene can replace manual task design by human experts, which is often limited and biased.
Implicationpartial
Directly stated in the analysis excerpt under 'disruption', presenting it as a key advantage of the method.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Robotic Task Automation

Competitors

not indexed

Competitive landscape

Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.

Segment

Robotic Task Automation

Adoption evidence

No public code link in the paper record yet

Commercial read

8.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.16444 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(50)

GAIA: Generating Task Instruction Aware Simulation Grounded in Real Contexts Using Vision-Language Models

2026Dogyu Ko, Chanyoung Yeo et al.

RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence

2025Chengkai Hou, Kun Wu et al.

AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning

2025Ran Gong, Xiaohan Zhang et al.

RoboCOIN: An Open-Sourced Bimanual Robotic Data COllection for INtegrated Manipulation

2025Shihan Wu, Xuecheng Liu et al.

XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations

2025Shichao Fan, Kun Wu et al.

X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

2025Jinliang Zheng, Jianxiong Li et al.

MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulation

2025Zhuoyang Liu, Jiaming Liu et al.

MolmoAct: Action Reasoning Models that can Reason in Space

2025Jason Lee, Jiafei Duan et al.

GR-3 Technical Report

2025Chi-Lam Cheang, Sijin Chen et al.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

2025Gheorghe Comanici, Eric Bieber et al.

ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making

2025Liu Dai, Haina Wang et al.

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

2025Qingwen Bu, Yanting Yang et al.

π0.5: a Vision-Language-Action Model with Open-World Generalization

2025Physical Intelligence, Kevin Black et al.

Phoenix: A Motion-Based Self-Reflection Framework for Fine-Grained Robotic Action Correction

2025Wenke Xia, Ruoxuan Feng et al.

AgiBot World Colosseo: A Large-Scale Manipulation Platform for Scalable and Intelligent Embodied Systems

2025AgiBot-World-Contributors, Qingwen Bu et al.

RCareGen: An Interface for Scene and Task Generation in RCareWorld

2025Shuaixing Chen, Ruolin Ye et al.

Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos

2025Weirui Ye, Fangchen Liu et al.

SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

2025Delin Qu, Haoming Song et al.

DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression

2025Junjie Wen, Yichen Zhu et al.

RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation

2024Kun Wu, Chengkai Hou et al.

Showing 20 of 50 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkRoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

8.0

Extension

Builds On ThisAtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models

7.0

Builds On ThisV-Dreamer: Automating Robotic Simulation and Trajectory Synthesis via Video Generation Priors

7.0

Builds On ThisRed-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies

7.0

Builds On ThisSoftMimicGen: A Data Generation System for Scalable Robot Learning in Deformable Object Manipulation

7.0

Builds On ThisRoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots

6.0

Builds On ThisManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation

7.0

Builds On ThisEscaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation

7.0

Builds On ThisScaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds

7.0

Builds On ThisRetrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs

4.0

Commercially relevant

none indexed

Conflicting

none indexed

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2602.16444
Route: /paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation
Active tab: read
Artifact: robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation/paper-pack
REST build passport API/api/v1/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "0f8ef3ba-1f32-4274-b599-a68d74a6cfd5",
  "arxiv_id": "2602.16444",
  "canonical_route": "/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation",
  "endpoints": {
    "paper_pack": "/api/v1/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation/paper-pack",
    "build_passport": "/api/v1/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation

degraded

Proof freshness: stale
Proof status: failed
Display score: 8/10
Last proof check: 2026-03-17
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 33%

This page has proof data, but the latest verification did not complete cleanly.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

Canonical ID robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation | Route /paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.16444"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation",
  "normalized_query": "2602.16444",
  "route": "/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation",
  "paper_ref": "robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Watch and verify: RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

/buildability/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation

Watchwatch

Subject: RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation

Paper ref

robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation

arXiv id

2602.16444

Freshness

Generated at

2026-03-17T19:46:04.153Z

Evidence freshness

stale

Last verification

2026-03-17T19:46:04.153Z

Sources

References

Coverage

33%

Hash state

Lineage hash

639278b0ad0b57bf51e3392a059511e0ac4665b25f5f207ccec2d595e37aa1c3

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation#webpage",
      "url": "https://sciencetostartup.com/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation",
      "name": "RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation",
      "description": "Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation#scholarlyArticle",
      "headline": "RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation",
      "description": "Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application.",
      "url": "https://sciencetostartup.com/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation",
      "sameAs": "https://arxiv.org/abs/2602.16444",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.16444"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-18T13:29:43.000Z",
      "author": [
        {
          "@type": "Person",
          "name": "Yixue Zhang",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Kun Wu",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Zhi Gao",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Institute of Technology"
          }
        },
        {
          "@type": "Person",
          "name": "Zhen Zhao",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Pei Ren",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Zhiyuan Xu",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Fei Liao",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Xinhua Wang",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Shichao Fan",
          "affiliation": {
            "@type": "Organization",
            "name": "The School of Mechanical Engineering and Automation, Beihang University"
          }
        },
        {
          "@type": "Person",
          "name": "Di Wu",
          "affiliation": {
            "@type": "Organization",
            "name": "State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University"
          }
        },
        {
          "@type": "Person",
          "name": "Qiuxuan Feng",
          "affiliation": {
            "@type": "Organization",
            "name": "State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University"
          }
        },
        {
          "@type": "Person",
          "name": "Meng Li",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Zhengping Che",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        },
        {
          "@type": "Person",
          "name": "Chang Liu",
          "affiliation": {
            "@type": "Organization",
            "name": "The School of Advanced Manufacturing and Robotics, Peking University"
          }
        },
        {
          "@type": "Person",
          "name": "Jian Tang",
          "affiliation": {
            "@type": "Organization",
            "name": "Beijing Innovation Center of Humanoid Robotics"
          }
        }
      ],
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "26028fc50841d00d3e5cc7be02643bba29377cf5"
          },
          "url": "https://www.semanticscholar.org/paper/26028fc50841d00d3e5cc7be02643bba29377cf5"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e1ca33eef264418148ab1192e73bf7df12e17b3e"
          },
          "url": "https://www.semanticscholar.org/paper/e1ca33eef264418148ab1192e73bf7df12e17b3e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1a970e5f657f39b9ea1a1c5188866129ad82e380"
          },
          "url": "https://www.semanticscholar.org/paper/1a970e5f657f39b9ea1a1c5188866129ad82e380"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8b7fcdeec84fc3d283d11e0507e6726a60e29628"
          },
          "url": "https://www.semanticscholar.org/paper/8b7fcdeec84fc3d283d11e0507e6726a60e29628"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "de35c00289bcec7c41cb1af27860208b45cdb04b"
          },
          "url": "https://www.semanticscholar.org/paper/de35c00289bcec7c41cb1af27860208b45cdb04b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9855c60d2ecdcf7edc4622ecd004f0db147fc22b"
          },
          "url": "https://www.semanticscholar.org/paper/9855c60d2ecdcf7edc4622ecd004f0db147fc22b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "19e7d97f0863cf6d519e1904e604d11ce3a3ec33"
          },
          "url": "https://www.semanticscholar.org/paper/19e7d97f0863cf6d519e1904e604d11ce3a3ec33"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "12d4e00d470d50701dceae24eacf616608c22ecd"
          },
          "url": "https://www.semanticscholar.org/paper/12d4e00d470d50701dceae24eacf616608c22ecd"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8e2fa8ab31d547b59706d88b33f044b0ee915003"
          },
          "url": "https://www.semanticscholar.org/paper/8e2fa8ab31d547b59706d88b33f044b0ee915003"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "39d9c3f1cd4bd5069713e50dc7301570575fc055"
          },
          "url": "https://www.semanticscholar.org/paper/39d9c3f1cd4bd5069713e50dc7301570575fc055"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "89101deaac8004e9a50116974a6077dc35f26911"
          },
          "url": "https://www.semanticscholar.org/paper/89101deaac8004e9a50116974a6077dc35f26911"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "23ec5b0184fe48558f14401247a411d2a48bd75f"
          },
          "url": "https://www.semanticscholar.org/paper/23ec5b0184fe48558f14401247a411d2a48bd75f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1e2a82ef5e0325a26ca0344c4f8c256c52fae7ec"
          },
          "url": "https://www.semanticscholar.org/paper/1e2a82ef5e0325a26ca0344c4f8c256c52fae7ec"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1b66c5272defac497384a3895b2b48e41cf83e29"
          },
          "url": "https://www.semanticscholar.org/paper/1b66c5272defac497384a3895b2b48e41cf83e29"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9d60da11b2af826310882f1a81e0b125c0600a00"
          },
          "url": "https://www.semanticscholar.org/paper/9d60da11b2af826310882f1a81e0b125c0600a00"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0d55823484046eba18a989ae2a7e08c66d1aac72"
          },
          "url": "https://www.semanticscholar.org/paper/0d55823484046eba18a989ae2a7e08c66d1aac72"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "2a2d8ef3a738d1f8b09593e6681483de98f6fa29"
          },
          "url": "https://www.semanticscholar.org/paper/2a2d8ef3a738d1f8b09593e6681483de98f6fa29"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "10301766e5686bda76722ef2af1362213b934cc0"
          },
          "url": "https://www.semanticscholar.org/paper/10301766e5686bda76722ef2af1362213b934cc0"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a4af09dfbb5a302d22408628ea4ac1ca5dc7993c"
          },
          "url": "https://www.semanticscholar.org/paper/a4af09dfbb5a302d22408628ea4ac1ca5dc7993c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0713b44a6232651671fd2fe572f892c25808332b"
          },
          "url": "https://www.semanticscholar.org/paper/0713b44a6232651671fd2fe572f892c25808332b"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 8
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Robotic Task Automation"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Robotic Task Automation",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "RoboGene: Boosting VLA Pre-training via Diversity-Driven Age",
          "item": "https://sciencetostartup.com/paper/robogene-boosting-vla-pre-training-via-diversity-driven-agentic-framework-for-real-world-task-generation"
        }
      ]
    },
    {
      "@type": "FAQPage",
      "mainEntity": [
        {
          "@type": "Question",
          "name": "What is the startup potential of \"RoboGene: Boosting VLA Pre-training via Diversity-Driven Age\"?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "Automate diverse and feasible robotic task generation with RoboGene for enhanced model pre-training and real-world application."
          }
        },
        {
          "@type": "Question",
          "name": "What products could be built from this research?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "To productize, RoboGene can be offered as a SaaS solution, where companies subscribe for access to a continuous stream of validated robotic tasks that match their specific environments and robot capabilities."
          }
        },
        {
          "@type": "Question",
          "name": "What are the practical use cases?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "RoboGene could be used by robotics companies to provide a steady supply of diverse training tasks for robots, improving their adaptability and functionality in unstructured environments like warehouses or manufacturing plants."
          }
        },
        {
          "@type": "Question",
          "name": "What industries could this research disrupt?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "RoboGene can replace manual task design by human experts, which is often limited and biased. This enables more efficient and scalable task preparation processes."
          }
        }
      ]
    }
  ]
}

RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(50)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(50)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline