Agentic Schema Discovery

• Agentic schema discovery is a process that autonomously identifies, constructs, and validates structured representations (schemas) in AI systems.
• It employs multi-agent architectures and formal protocols to propose, critique, and integrate schemas across various domains such as databases, task planning, and scientific theory revision.
• The approach demonstrates measurable improvements in precision, recall, and operational efficiency, enhancing system interpretability and scalability in real-world applications.

Agentic schema discovery refers to the autonomous or semi-autonomous identification, construction, refinement, and registration of structured representations (“schemas”) of tasks, data, workflows, or capabilities by agentic AI systems or multi-agent collectives. Such discovery processes span domains from database schema distillation and multimodal ontology extraction to capability registries and scientific theory revision, but always center on deliberate, architecture-mediated procedures by which agents build, expose, and validate operational schemata. This article provides a comprehensive analysis of the formal principles, architectures, multi-agent protocols, evaluation criteria, and representative domains for agentic schema discovery.

1. Formal Foundations and Definitions

In agentic settings, a schema may denote a database view, task signature, workflow capability, entity-attribute schema, or even the categorical typing regime underlying a discovery system. Across implementations, two defining characteristics prevail. First, agents operate over a formal space of types, signatures, or APIs—schema objects that structure how data, actions, and knowledge are represented. Second, schema discovery is not the mere reading or instantiation of a fixed schema, but an agent-mediated process whereby new schemas are proposed, validated, and possibly assimilated into global registries or semantic layers (Rissaki et al., 2024, Muscariello et al., 23 Sep 2025, Payne et al., 18 May 2026, Wang et al., 31 May 2026).

A canonical formalization involves types $S$ (e.g., table sets, action signatures, schema categories), structured artifacts or entries $I: S \to \mathrm{Set}$, and operations $f: S \to S'$ for schema revision or extension. In database systems, a schema is modeled as a graph $G = (T, E)$ with tables $T$ and foreign-key edges $E$; in agentic directories, schemas are versioned, typed objects indexed under taxonomies; in categorical discovery systems, the schema category $S_b$ is the domain of artifact types and operations (Rissaki et al., 2024, Muscariello et al., 23 Sep 2025, Wang et al., 31 May 2026).

2. Multi-Agent Architectures and Collaborative Protocols

Agentic schema discovery is frequently orchestrated via multi-agent protocols involving role-specialized agents and explicit turn-taking. In large-scale database refinement, three core LLM agents—ViewProposer, ViewEvaluator, SchemaRefiner—operate asynchronously: proposing new views given local schema context, evaluating proposals for semantic and syntactic clarity, and verifying executable correctness with actual queries (Rissaki et al., 2024). The chat manager enforces consistent message passing and orchestrates iterative convergence based on an explicit objective function that trades off interpretability and complexity:

$$J(S) = \sum_{v \in S} \mathrm{Quality}(v) - \lambda \sum_{v \in S} \mathrm{Complexity}(v)$$

Other agentic frameworks—such as TabAgent for workflow classification or DALIA for multi-agent task orchestration—replace generative agent components with discriminative classifiers or enforce deterministic, schema-declared task graphs by grounding all tasks and capabilities in signed directory entries (Rodriguez-Sanchez et al., 24 Jan 2026, Levy et al., 18 Feb 2026). Each protocol stresses separation of concerns: discovery is a formal, traceable, and verifiable process over an explicit schema or capability space.

The table below summarizes archetypal agent roles in representative agentic schema discovery frameworks:

Framework	Agent/Affordance Roles	Main Responsibilities
Agentic Database	ViewProposer, ViewEvaluator, Refiner	Propose, critique, verify SQL views
DALIA	Orchestrator, Directory Agents	Compose deterministic, declared task graphs
TabAgent	TabSchema, TabHead	Extract features, classifier-based selection
Categorical Sci	Builder, Breaker, Gate/Verifier	Propose, stress test, and audit schema change

3. Schema Types and Representation Modalities

Agentic schema discovery encompasses a broad spectrum of schema representation types, including:

• Database Views and Semantic Layers: Lightweight, interpretable SQL views constructed from unwieldy enterprise schemas; the union of materialized views forms a semantic layer that enhances downstream interpretability and query accuracy (Rissaki et al., 2024).
• Task and Capability Schemas: Task schemas $T$ and capability tuples $C$ as in DALIA, typically include unique IDs, roles, domains, input/output signature, preconditions, and postconditions. All graph-construction and planning is restricted to these declaratively registered schemas (Rodriguez-Sanchez et al., 24 Jan 2026).
• Entity-Attribute Schemas: In multimodal discovery (RAVEN), schemas define entity types and attribute lists per domain or category, guiding structured extraction in video, audio, or text domains (Rosa, 3 Mar 2025).
• Classifiers over Schema Features: In TabAgent, an “agentic schema” is realized as a feature vector $I: S \to \mathrm{Set}$0 comprising static, state, and dependency features, enabling discriminative modeling of agent decision points (Levy et al., 18 Feb 2026).
• Categorical/Type-Theoretic Schemas: Discovery systems formalize the typology of artifacts and operations as a category $I: S \to \mathrm{Set}$1; schema discovery is a regime transition $I: S \to \mathrm{Set}$2, governed by functorial transport and residual comparison (Wang et al., 31 May 2026).
• Capability Registries and Directories: MAS agents register schemas according to multi-dimensional taxonomies (skills, domains, features), and discovery is realized as a federated, cryptographically verifiable lookup (Muscariello et al., 23 Sep 2025).

4. Protocols for Discovery, Validation, and Integration

Discovery processes often interleave proposal, validation, and integration phases as orchestrated workflows:

• Sampling and Chunking: Input schemas or artifact graphs are algorithmically partitioned into subgraphs (e.g., via random walk or GraphRAG) to ensure manageable context for agent teams (Rissaki et al., 2024, Srinivas et al., 2024).
• Asynchronous Multi-agent Conversations: Proposals are iteratively generated, critiqued, modified, and validated until an objective $I: S \to \mathrm{Set}$3 is reached or no further proposals emerge (Rissaki et al., 2024). Execution correctness is enforced by validating candidate schemas/view definitions against actual database engines or via code extraction and judge review in classifier pipelines (Levy et al., 18 Feb 2026).
• Registry-based Constraint: In agent directories, discovery proceeds via lookup and intersection over three orthogonal axes: skills, domains, features. Each canonical schema is indexed by a unique content identifier, discoverable via distributed hash table (DHT) lookup and validated with cryptographic signatures (Muscariello et al., 23 Sep 2025).
• Semantic Validation and Deduplication: Post-processing includes embedding and clustering of views or entities, deduplication of schemas, alignment with domain constraints, and annotation of entities or relationships via additional agents or rule-engines (Rissaki et al., 2024, Srinivas et al., 2024).
• Dynamic Categorical Lifting: In scientific domains, regime transitions are executed via left Kan extensions and the residual defines genuinely new, discovered schema content—not reconstructible as functorial transport from the old regime (Wang et al., 31 May 2026).

5. Evaluation Metrics, Practical Outcomes, and Scaling

Agentic schema discovery is empirically evaluated via a range of precision, recall, interpretability, efficiency, and compliance metrics. For example, on the Braze database, the agentic pipeline distilled 1,146 views covering over 80% of original columns with high view precision (0.94) and recall (0.88), compared to conventional schema mining tools (Rissaki et al., 2024). In TabAgent, substituting generative shortlisters with classifier heads based on schema and trajectory features attained P@R ≥ 0.92, reduced inference latency by ≈95%, and inference cost by up to 91% (Levy et al., 18 Feb 2026).

Scalability strategies include parallelizing over sampled schema subgraphs, caching context embeddings, deduplicating previously discovered schema elements, and tuning hyperparameters to optimize trade-offs between interpretability and succinctness (Rissaki et al., 2024). Integrity is routinely enforced by constraining schema proposal/registration to signed and versioned objects managed by tamper-evident registries with clear separation between index and locator distributions (Muscariello et al., 23 Sep 2025).

Best practices include:

• Limiting subgraph schema context to 5–10 tables to bound LLM input size.
• Using vector indices or content embeddings for fast retrieval of relevant context.
• Employing provenance and result-executability checks at each schema proposal stage.
• Mitigating generative errors (e.g., hallucinations) by requiring execution-based verification of all proposed views or capabilities.

6. Illustrative Application Domains

Agentic schema discovery is deployed across a spectrum of computational and scientific domains:

• Enterprise Database Refinement: Deployment in commercial database settings, producing semantic layers that markedly improve coverage, interpretability, and downstream Text-to-SQL system performance (Rissaki et al., 2024).
• Multi-agent Capability Registries: Extensible agent directories for heterogeneous multi-agent systems and federated AI services, supporting verifiable, multi-dimensional capability discovery via the Open Agentic Schema Framework and DHT-based content addressing (Muscariello et al., 23 Sep 2025).
• Scientific Discovery Systems: Categorical frameworks enabling AI systems to revise their representational schema, provably identifying new content not functorially transportable from previous regimes (Wang et al., 31 May 2026).
• Multimodal Video and Entity Discovery: RAVEN's modular pipeline that produces dynamic, domain-specific schemas for efficient entity extraction across massive video datasets (Rosa, 3 Mar 2025).
• Task Planning and Deterministic Orchestration: DALIA’s model for partitioning agent workflows into discovery, planning, and execution over a closed declarative schema, eschewing speculative plan synthesis for verifiable, reproducible agentic processes (Rodriguez-Sanchez et al., 24 Jan 2026).
• Industrial Process Engineering: Automated agentic pipelines for synthesizing regulation-compliant process diagrams, with schemas constructed and validated by multi-agent collaboration and retrieval-augmented knowledge graph construction (Srinivas et al., 2024).

7. Limitations, Research Directions, and Conclusion

Agentic schema discovery inherits limitations from both LLM-driven generation and registry-based constraint. LLM agents may hallucinate spurious relations absent rigorous execution or registry-based validation protocols (Rissaki et al., 2024). Scalability is modulated by the efficiency of schema partitioning, classifier replacement, and context management. Registry-driven discovery requires robust taxonomy governance and version control to maintain composability across emergent modalities (Muscariello et al., 23 Sep 2025).

Research frontiers include:

• Formalization and enforcement of compositional affordance semantics in federated schema discovery (Payne et al., 18 May 2026).
• Efficient approximations for high-expressivity schema grounding and verification (Payne et al., 18 May 2026).
• Dynamic, audit-friendly tracking of regime transitions in self-revising discovery systems (Wang et al., 31 May 2026).
• Integration of interactive GUI feedback and human-in-the-loop schema annotation (Rissaki et al., 2024).
• Generalization to cross-domain, multimodal, and discourse-layer schema discovery protocols (Rosa, 3 Mar 2025, Xu et al., 1 Feb 2026).

Agentic schema discovery thus constitutes a foundational capability for scalable, interoperable, and verifiable AI systems, supporting flexible, semantically transparent composition across tasks, modalities, and domains (Rissaki et al., 2024, Muscariello et al., 23 Sep 2025, Wang et al., 31 May 2026).