NormCode Canvas: Making LLM Agentic Workflows Development Sustainable via Case-Based Reasoning

2026-03-13

AI Summary

This work addresses the limitations of conventional large language model (LLM) workflows, which suffer from unreliable retrieval, difficulty in fault localization, and limited evolvability due to implicit state sharing. To overcome these challenges, the authors propose a sustainable LLM agent workflow system grounded in two-level case-based reasoning. Each execution checkpoint is encapsulated as a self-contained case using NormCode, a semi-formal planning language, and compiler-verified scoping rules ensure case independence, enabling reuse, revision, and recursive learning. The system supports direct checkpoint inspection, narrative pre-review, and scoped re-execution, thereby establishing a self-sustaining ecosystem capable of cumulative learning. The approach is deployed across four distinct workflows—presentation generation, multi-turn code assistance, natural language to NormCode compilation, and Canvas debugging—forming a closed loop of mutual generation, debugging, and optimization.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• 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
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

We present NormCode Canvas (v1.1.3), a deployed system realizing Case-Based Reasoning at two levels for multi-step LLM workflows. The foundation is NormCode, a semi-formal planning language whose compiler-verified scope rule ensures every execution checkpoint is a genuinely self-contained case -- eliminating the implicit shared state that makes retrieval unreliable and failure non-localizable in standard orchestration frameworks. Level 1 treats each checkpoint as a concrete case (suspended runtime); Fork implements retrieve-and-reuse, Value Override implements revision with automatic stale-boundary propagation. Level 2 treats each compiled plan as an abstract case; the compilation pipeline is itself a NormCode plan, enabling recursive case learning. Three structural properties follow: (C1) direct checkpoint inspection; (C2) pre-execution review via compiler-generated narrative; (C3) scope-bounded selective re-execution. Four deployed plans serve as structured evidence: PPT Generation produces presentation decks at ~40s per slide on commercial APIs; Code Assistant carries out multi-step software-engineering tasks spanning up to ten reasoning cycles; NC Compilations converts natural-language specifications into executable NormCode plans; and Canvas Assistant, when connected to an external AI code editor, automates plan debugging. Together these plans form a self-sustaining ecosystem in which plans produce, debug, and refine one another -- realizing cumulative case-based learning at system scale.

Problem

• LLM agentic workflows
• Case-Based Reasoning
• sustainable development
• shared state
• workflow orchestration

Innovation

• Case-Based Reasoning
• NormCode
• LLM Agentic Workflows
• Scope-Bounded Execution
• Recursive Plan Compilation