ARXIV:2604.07041 · AI IN DATABASES · SUBMITTED 09 APR · 20:33 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: partial proof status

AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

Q: What products could be built from this research?

AV-SQL can be productized as an API within existing database management systems or as a feature in data analytics platforms that offers natural language query capabilities, making complex data analysis more accessible.

Q: What are the practical use cases?

Integrate AV-SQL into business intelligence tools to enable users to query internal databases using natural language, boosting productivity for teams who need rapid data access without SQL skills.

Q: What industries could this research disrupt?

AV-SQL could replace traditional query building tools and manual SQL coding, drastically simplifying data access in complex systems and empowering non-technical users.

Minh Tam Pham · Trinh Pham · Tong Chen · Hongzhi Yin · Quoc Viet Hung Nguyen · Thanh Tam Nguyen · arXiv

AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

Ship in 2-4 weeks›Score8.0Evidence partial

Opportunity summary

Pain AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

Evidence 59 refs | 4 sources | 100% coverage

Blocker Evidence partial

Open Build Read PDF Signal Canvas Track

PROBLEM

AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach. Despite rapid advances driven by large language models (LLMs), existing approaches still struggle with complex queries in real-world…

METHOD

Full abstract

Text-to-SQL is the task of translating natural language queries into executable SQL for a given database, enabling non-expert users to access structured data without writing SQL manually. Despite rapid advances driven by large language models (LLMs), existing approaches still struggle with complex queries in real-world settings, where database schemas are large and questions require multi-step reasoning over many interrelated tables. In such cases, providing the full schema often exceeds the context window, while one-shot generation frequently produces non-executable SQL due to syntax errors and incorrect schema linking. To address these challenges, we introduce AV-SQL, a framework that decomposes complex Text-to-SQL into a pipeline of specialized LLM agents. Central to AV-SQL is the concept of agentic views: agent-generated Common Table Expressions (CTEs) that encapsulate intermediate query logic and filter relevant schema elements from large schemas. AV-SQL operates in three stages: (1) a rewriter agent compresses and clarifies the input query; (2) a view generator agent processes schema chunks to produce agentic views; and (3) a planner, generator, and revisor agent collaboratively compose these views into the final SQL query. Extensive experiments show that AV-SQL achieves 70.38% execution accuracy on the challenging Spider 2.0 benchmark, outperforming state-of-the-art baselines, while remaining competitive on standard datasets with 85.59% on Spider, 72.16% on BIRD and 63.78% on KaggleDBQA. Our source code is available at https://github.com/pminhtam/AV-SQL.

RESULT

ScienceToStartup currently rates this 8.0/10 on the public viability pass. Extensive experiments show that AV-SQL achieves 70.38% execution accuracy on the challenging Spider 2.0 benchmark, outperforming state-of-the-art baselines, while remaining competitive on standard datasets…

WHY NOW

AI in Databases moved forward this cycle; last verified April 2026. Public score 8.0/10. Implementation evidence is present through a linked repository.

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

Opportunity summary

Score8.0

PainAV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

Evidence59 refs | 4 sources | 100% coverage

Blockerno shell-level blocker reported

Analysis summary

AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: partial proof status

ARXIV:2604.07041 · AI IN DATABASES · SUBMITTED 09 APR · 20:33 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: partial proof status

AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

Minh Tam Pham · Trinh Pham · Tong Chen · Hongzhi Yin · Quoc Viet Hung Nguyen · Thanh Tam Nguyen · arXiv

AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

Ship in 2-4 weeks›Score8.0Evidence partial

Opportunity summary

Pain AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

Evidence 59 refs | 4 sources | 100% coverage

Blocker Evidence partial

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

AI in Databases moved forward this cycle; last verified April 2026. Public score 8.0/10. Implementation evidence is present through a linked repository.

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

Opportunity summary

Score8.0

PainAV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

Evidence59 refs | 4 sources | 100% coverage

Blockerno shell-level blocker reported

Analysis summary

AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: partial proof status

Paper Pack

10.48550/arXiv.2604.07041

AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Parse run linked

A document parse run is attached to this paper.

Proof status

partial

59 refs; 4 sources; 100% coverage.

What was readable

linkedon file20 anchorsderived fallback24 indexednot indexed

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

Viability

8.0

Time to MVP

MVP estimate missing

Commercial

coderepo url

Export

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

AI in Databases moved forward this cycle; last verified April 2026. Public score 8.0/10. Implementation evidence is present through a linked repository.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach. Despite rapid advances driven by large language models (LLMs), existing approaches still struggle with complex queries in real-world settings, where database schemas are large and questions require multi-step reasoning over many interrelated tables.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Text-to-SQL is the task of translating natural language queries into executable SQL for a given database, enabling non-expert users to access structured data without writing SQL manually. Despite rapid advances driven by large language models (LLMs), existing approaches still struggle with complex queries in real-world settings, where database schemas are large and questions require multi-step reasoning over many interrelated tables.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 8.0/10 on the public viability pass. Extensive experiments show that AV-SQL achieves 70.38% execution accuracy on the challenging Spider 2.0 benchmark, outperforming state-of-the-art baselines, while remaining competitive on standard datasets with 85.59% on Spider, 72.16% on BIRD and 63.78% on KaggleDBQA. A public repository is linked, so build verification can inspect implementation evidence instead of treating the paper as PDF-only.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
AI in Databases moved forward this cycle; last verified April 2026. Public score 8.0/10. Implementation evidence is present through a linked repository.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
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 linkedDocument parse run

Markets

AI in Databases

Competitors

not indexed

Competitive landscape

AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.

Segment

AI in Databases

Adoption evidence

Public code linked for build inspection

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 2604.07041 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(24)

Reference metadata pending (d5563870a06d23c5ac83531fbfbbe4ffb083631c)

Reference metadata pending (a37cea825dec002b91a549eacaf18558780832ad)

Reference metadata pending (c99f2f7a0ace5578ec779d6a7e67efe0cc520d34)

Reference metadata pending (9776b004fcc40f2d469dc0a34b2f2c342b99adab)

Reference metadata pending (ab649ecce8e85a7ac00e1cce9c1e4b605c1d8d0a)

Reference metadata pending (695c5cfed77b3128d943c598ababad48744fd631)

Reference metadata pending (0888915b05fdcbc519daeec7f6ab817212d642ca)

Reference metadata pending (978040c55f9094212d15b7ffadfab1440913b6cf)

Reference metadata pending (ba454ba8c594dfb86c25dff2e265c8a2686aa037)

Reference metadata pending (e034b664362640cc88dfa5e2e11c0524fc7cb323)

Reference metadata pending (104b0bb1da562d53cbda87aec79ef6a2827d191a)

Reference metadata pending (01de0020c6a0f2d0aa73965e8dcfd9b8f38e05b6)

Reference metadata pending (cc0f0cb09a73f82ed44d900f5ca710bec784acc1)

Reference metadata pending (6034a1ed44de01ffc18cd2265223ed2bf1d216cd)

Reference metadata pending (a4867148c2f692efc6c22c3935a59be2d04ea3e9)

Reference metadata pending (6d51f4b220cb2c8321dc5f9755b7d66f10f1cad6)

Reference metadata pending (e817b79f3d1ce0add9cb9b653d91af378f1dea18)

Reference metadata pending (5a3c1afe73d8bcc8288d17cb17be2baec8a98464)

Reference metadata pending (14793aa93920cb8f748776cc45c3895de6df5fbf)

Reference metadata pending (9cd3d6eef7c574830be410598c3024191ee974d4)

Showing 20 of 24 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 WorkPV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents

8.0

Prior WorkAn Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data

8.0

Extension

Builds On ThisSQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation

3.0

Builds On ThisCA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation

7.0

Builds On ThisAgent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems

7.0

Builds On ThisSemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesis

7.0

Builds On ThisTRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas

7.0

Builds On ThisBeyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs

5.0

Builds On ThisSPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables

7.0

Commercially relevant

Higher ViabilityChatSVA: Bridging SVA Generation for Hardware Verification via Task-Specific LLMs

9.0

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: 2604.07041
Route: /paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views
Active tab: read
Artifact: av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views

Available agents

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

API/MCP endpoints

REST paper pack API/api/v1/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views/paper-pack
REST build passport API/api/v1/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views/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": "ccc5ae39-34f0-4745-9885-7865f67f29f6",
  "arxiv_id": "2604.07041",
  "canonical_route": "/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views",
  "endpoints": {
    "paper_pack": "/api/v1/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views/paper-pack",
    "build_passport": "/api/v1/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views/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/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views

stale

Proof freshness: stale
Proof status: partial
Display score: 8/10
Last proof check: 2026-04-09
Score updated: 2026-04-09
Score fresh until: 2026-05-09
References: 59
Source count: 4
Coverage: 100%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

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

Agent Handoff

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

Agent Handoff

AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

Canonical ID av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views | Route /paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2604.07041"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views",
  "normalized_query": "2604.07041",
  "route": "/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views",
  "paper_ref": "av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views",
  "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

Ready for execution: AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

/buildability/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views

Build Nowready

Subject: AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

Verdict

Build Now

Verdict is Build Now because viability and implementation proof cleared the Wave 1 scaffold thresholds.

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/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views

Paper ref

av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views

arXiv id

2604.07041

Freshness

Generated at

2026-04-09T20:33:16.236Z

Evidence freshness

stale

Last verification

2026-04-09T20:33:16.236Z

Sources

References

Coverage

100%

Hash state

Lineage hash

40176492ac79104249da3bfddee6ef7e234e8cd9fd19d1601105791c2555d8c8

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

No explicit blockers are present in this receipt window.

59 refs / 4 sources / Verification pending

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.

Source proof

Visual citation anchors from the paper document graph.

20 anchors

proof blockPage 368%

This equation captures one of the core mathematical components of the system. define the database as D = (T, C, R), where T = {T1, T2, . . . , T𝑚}

Page and bbox are available; crop image is pending.

proof blockPage 668%

This equation captures one of the core mathematical components of the system. Formally, the overall rewriting objective is: Qrewrite = 𝐿𝐿𝑀𝑅𝑒𝑤𝑟𝑖𝑡𝑒𝑟 Q, K | Q For each literal ℓ∈L 𝑗 CTE, we retrieve an

Page and bbox are available; crop image is pending.

proof blockPage 668%

This equation captures one of the core mathematical components of the system. V 𝑗 CTE, J 𝑗= 𝐿𝐿𝑀𝑗 𝑉𝑖𝑒𝑤 Qrewrite, S𝑗 sub • If the JSON output selects no columns an

Page and bbox are available; crop image is pending.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views#webpage",
      "url": "https://sciencetostartup.com/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views",
      "name": "AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views",
      "description": "AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views#scholarlyArticle",
      "headline": "AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views",
      "description": "AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.",
      "url": "https://sciencetostartup.com/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views",
      "sameAs": "https://arxiv.org/abs/2604.07041",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2604.07041"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-04-08T12:56:13.000Z",
      "author": [
        {
          "@type": "Person",
          "name": "Minh Tam Pham",
          "affiliation": {
            "@type": "Organization",
            "name": "Griffith University"
          }
        },
        {
          "@type": "Person",
          "name": "Trinh Pham",
          "affiliation": {
            "@type": "Organization",
            "name": "Griffith University"
          }
        },
        {
          "@type": "Person",
          "name": "Tong Chen",
          "affiliation": {
            "@type": "Organization",
            "name": "The University of Queensland"
          }
        },
        {
          "@type": "Person",
          "name": "Hongzhi Yin",
          "affiliation": {
            "@type": "Organization",
            "name": "The University of Queensland"
          }
        },
        {
          "@type": "Person",
          "name": "Quoc Viet Hung Nguyen",
          "affiliation": {
            "@type": "Organization",
            "name": "Griffith University"
          }
        },
        {
          "@type": "Person",
          "name": "Thanh Tam Nguyen",
          "affiliation": {
            "@type": "Organization",
            "name": "Griffith University"
          }
        }
      ],
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d5563870a06d23c5ac83531fbfbbe4ffb083631c"
          },
          "url": "https://www.semanticscholar.org/paper/d5563870a06d23c5ac83531fbfbbe4ffb083631c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a37cea825dec002b91a549eacaf18558780832ad"
          },
          "url": "https://www.semanticscholar.org/paper/a37cea825dec002b91a549eacaf18558780832ad"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "c99f2f7a0ace5578ec779d6a7e67efe0cc520d34"
          },
          "url": "https://www.semanticscholar.org/paper/c99f2f7a0ace5578ec779d6a7e67efe0cc520d34"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9776b004fcc40f2d469dc0a34b2f2c342b99adab"
          },
          "url": "https://www.semanticscholar.org/paper/9776b004fcc40f2d469dc0a34b2f2c342b99adab"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ab649ecce8e85a7ac00e1cce9c1e4b605c1d8d0a"
          },
          "url": "https://www.semanticscholar.org/paper/ab649ecce8e85a7ac00e1cce9c1e4b605c1d8d0a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "695c5cfed77b3128d943c598ababad48744fd631"
          },
          "url": "https://www.semanticscholar.org/paper/695c5cfed77b3128d943c598ababad48744fd631"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0888915b05fdcbc519daeec7f6ab817212d642ca"
          },
          "url": "https://www.semanticscholar.org/paper/0888915b05fdcbc519daeec7f6ab817212d642ca"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "978040c55f9094212d15b7ffadfab1440913b6cf"
          },
          "url": "https://www.semanticscholar.org/paper/978040c55f9094212d15b7ffadfab1440913b6cf"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ba454ba8c594dfb86c25dff2e265c8a2686aa037"
          },
          "url": "https://www.semanticscholar.org/paper/ba454ba8c594dfb86c25dff2e265c8a2686aa037"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e034b664362640cc88dfa5e2e11c0524fc7cb323"
          },
          "url": "https://www.semanticscholar.org/paper/e034b664362640cc88dfa5e2e11c0524fc7cb323"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "104b0bb1da562d53cbda87aec79ef6a2827d191a"
          },
          "url": "https://www.semanticscholar.org/paper/104b0bb1da562d53cbda87aec79ef6a2827d191a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "01de0020c6a0f2d0aa73965e8dcfd9b8f38e05b6"
          },
          "url": "https://www.semanticscholar.org/paper/01de0020c6a0f2d0aa73965e8dcfd9b8f38e05b6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "cc0f0cb09a73f82ed44d900f5ca710bec784acc1"
          },
          "url": "https://www.semanticscholar.org/paper/cc0f0cb09a73f82ed44d900f5ca710bec784acc1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6034a1ed44de01ffc18cd2265223ed2bf1d216cd"
          },
          "url": "https://www.semanticscholar.org/paper/6034a1ed44de01ffc18cd2265223ed2bf1d216cd"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a4867148c2f692efc6c22c3935a59be2d04ea3e9"
          },
          "url": "https://www.semanticscholar.org/paper/a4867148c2f692efc6c22c3935a59be2d04ea3e9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6d51f4b220cb2c8321dc5f9755b7d66f10f1cad6"
          },
          "url": "https://www.semanticscholar.org/paper/6d51f4b220cb2c8321dc5f9755b7d66f10f1cad6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "e817b79f3d1ce0add9cb9b653d91af378f1dea18"
          },
          "url": "https://www.semanticscholar.org/paper/e817b79f3d1ce0add9cb9b653d91af378f1dea18"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5a3c1afe73d8bcc8288d17cb17be2baec8a98464"
          },
          "url": "https://www.semanticscholar.org/paper/5a3c1afe73d8bcc8288d17cb17be2baec8a98464"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "14793aa93920cb8f748776cc45c3895de6df5fbf"
          },
          "url": "https://www.semanticscholar.org/paper/14793aa93920cb8f748776cc45c3895de6df5fbf"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9cd3d6eef7c574830be410598c3024191ee974d4"
          },
          "url": "https://www.semanticscholar.org/paper/9cd3d6eef7c574830be410598c3024191ee974d4"
        }
      ],
      "codeRepository": "https://github.com/pminhtam/AV-SQL",
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 8
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "AI in Databases"
        },
        {
          "@type": "PropertyValue",
          "propertyID": "commercialReadiness",
          "value": "code, repo url"
        }
      ]
    },
    {
      "@type": "SoftwareSourceCode",
      "@id": "https://sciencetostartup.com/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views#software",
      "name": "AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views - Source Code",
      "description": "AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach.",
      "codeRepository": "https://github.com/pminhtam/AV-SQL",
      "url": "https://github.com/pminhtam/AV-SQL"
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "AI in Databases",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic",
          "item": "https://sciencetostartup.com/paper/av-sql-decomposing-complex-text-to-sql-queries-with-agentic-views"
        }
      ]
    },
    {
      "@type": "FAQPage",
      "mainEntity": [
        {
          "@type": "Question",
          "name": "What is the startup potential of \"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic\"?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "AV-SQL simplifies complex Text-to-SQL queries for large database schemas using a novel agentic view decomposition approach."
          }
        },
        {
          "@type": "Question",
          "name": "What products could be built from this research?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "AV-SQL can be productized as an API within existing database management systems or as a feature in data analytics platforms that offers natural language query capabilities, making complex data analysis more accessible."
          }
        },
        {
          "@type": "Question",
          "name": "What are the practical use cases?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "Integrate AV-SQL into business intelligence tools to enable users to query internal databases using natural language, boosting productivity for teams who need rapid data access without SQL skills."
          }
        },
        {
          "@type": "Question",
          "name": "What industries could this research disrupt?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "AV-SQL could replace traditional query building tools and manual SQL coding, drastically simplifying data access in complex systems and empowering non-technical users."
          }
        }
      ]
    }
  ]
}

AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(24)

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(24)

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