Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows

2026-03-04

AI Summary

This work addresses the lack of structured, type-safe, and interpretable data workflows in enterprise-grade AI agent systems, particularly concerning reliability, scalability, and observability. The authors propose a lightweight, Python-native framework that models large language model inference as typed semantic transformations—formalized as transductions—grounded in logical transduction algebra. The framework introduces algebraic operators to enable composition and parallel execution of these transductions while guaranteeing type safety, evidence locality, stateless parallelism, and semantic traceability between inputs and outputs. Empirical evaluation on benchmarks such as DiscoveryBench and Archer demonstrates state-of-the-art performance, validating the approach’s effectiveness in data discovery and natural language-to-SQL tasks.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Agentic AI is rapidly transitioning from research prototypes to enterprise deployments, where requirements extend to meet the software quality attributes of reliability, scalability, and observability beyond plausible text generation. We present Agentics 2.0, a lightweight, Python-native framework for building high-quality, structured, explainable, and type-safe agentic data workflows. At the core of Agentics 2.0, the logical transduction algebra formalizes a large language model inference call as a typed semantic transformation, which we call a transducible function that enforces schema validity and the locality of evidence. The transducible functions compose into larger programs via algebraically grounded operators and execute as stateless asynchronous calls in parallel in asynchronous Map-Reduce programs. The proposed framework provides semantic reliability through strong typing, semantic observability through evidence tracing between slots of the input and output types, and scalability through stateless parallel execution. We instantiate reusable design patterns and evaluate the programs in Agentics 2.0 on challenging benchmarks, including DiscoveryBench for data-driven discovery and Archer for NL-to-SQL semantic parsing, demonstrating state-of-the-art performance.

Problem

• Agentic AI
• software quality attributes
• reliability
• scalability
• observability

Innovation

• logical transduction algebra
• transducible function
• type-safe agentic workflows
• semantic observability
• stateless parallel execution