Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows

Alfio Massimiliano Gliozzo, Junkyu Lee, Nahuel Defosse

TL;DR

This work presents Agentics 2.0, a lightweight, Python-native framework for building high-quality, structured, explainable, and type-safe agentic data workflows, and instantiates reusable design patterns and evaluates the programs in Agentics 2.0 on challenging benchmarks, demonstrating state-of-the-art performance.

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.

Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows

TL;DR

This work presents Agentics 2.0, a lightweight, Python-native framework for building high-quality, structured, explainable, and type-safe agentic data workflows, and instantiates reusable design patterns and evaluates the programs in Agentics 2.0 on challenging benchmarks, demonstrating state-of-the-art performance.

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.
Paper Structure (42 sections, 7 equations, 4 figures, 2 tables)

This paper contains 42 sections, 7 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Logical Transduction Algebra
  3. Background
  4. Types as Semantically Grounded Objects
  5. Transducible Functions
  6. Algebraic Structure of Transducible Functions
  7. Identity and Associativity.
  8. Composition.
  9. Canonical Type Transductions.
  10. Map-Reduce Semantics
  11. Map.
  12. Reduce.
  13. Map-Reduce.
  14. Agentics 2.0
  15. The << Operator
  16. ...and 27 more sections

Figures (4)

  • Figure 1: Overall aggregated scores. All figures show the aggregated scores over 10 problem domains, evaluating agentics-agg (ag-agg), agentics-both (ag-both), agentics-react (ag-react), and baseline-react (bl-react) using gemini-3-flash-previuew (gemini3flash) and gpt-4.1 (gpt4.1) models.
  • Figure 2: Aggregated scores per dataset. All figures show the aggregated hypothesis matching scores per each dataset, and show the results from four algorithm configurations agentics-agg (ag-agg), agentics-both (ag-both), agentics-react (ag-react), and baseline-react (bl-react).
  • Figure 3: Aggregated scores per question types. All figures show the aggregated scores for three question types: context questions, relationship questions, and variable questions.
  • Figure 4: Archer English Devset Execution Match. The figure shows the aggregated execution match score on the English devest, and shows the results from Agentics 2.0 implementation in blue bars and the Archer leaderboard results in orange bars.

Theorems & Definitions (1)

  • Example 1