A Literate Programming Environment for Human and Machine Agents

Adam T. Burke

cs.SEAug 25, 2026

A Literate Programming Environment for Human and Machine Agents

Authors: Adam T. Burke

Organizations: Queensland University of Technology, Brisbane, Queensland, Australia

Abstract

This paper introduces an environment for constructing literate programs in concert with language-aware machine agents. This environment includes a grammar for executable program essays, a parser that treats names as first-class objects, an internal name-graph which relates prose, names and executable artifacts, and a binding mechanism for existing languages and testing toolsets. This supports co-location of code with its most relevant natural language and structured data context, making better use of Large Language Model (LLM) context windows. It also provides LLM coding agents with a toolset more analogous to the symbol-aware search and usage information available in human programmer-facing Integrated Development Environments (IDEs). We describe a working implementation with bindings to three established programming languages, and several example programs.

Figures & tables

$\displaystyle\langle\textrm{start}\rangle$	$\displaystyle::=$	$\displaystyle\langle\textrm{module}\rangle$
$\displaystyle\langle\textrm{module}\rangle$	$\displaystyle::=$	$\displaystyle\langle\textrm{MOD\_HEAD}\rangle\;\langle\textrm{body}\rangle\;[\,\langle\textrm{post\_text}\rangle\,]$
$\displaystyle\langle\textrm{body}\rangle$	$\displaystyle::=$	$\displaystyle\{\,\langle\textrm{body\_item}\rangle\,\}$
$\displaystyle\langle\textrm{body\_item}\rangle$	$\displaystyle::=$	$\displaystyle\langle\textrm{subheading}\rangle$
		$\displaystyle\;\mid\;\langle\textrm{code\_block}\rangle$
		$\displaystyle\;\mid\;\langle\textrm{claim}\rangle$
		$\displaystyle\;\mid\;\langle\textrm{prose\_block}\rangle$

Figure 2. Notlob grammar - Productions. Grammar listing.

$\displaystyle\langle\textrm{LINE\_CHAR}\rangle$	$\displaystyle::=$	any character other than newline
$\displaystyle\langle\textrm{REST\_OF\_LINE}\rangle$	$\displaystyle::=$	$\displaystyle\{\,\langle\textrm{LINE\_CHAR}\rangle\,\}\;\langle\textrm{NewLine}\rangle$
$\displaystyle\langle\textrm{MOD\_HEAD}\rangle$	$\displaystyle::=$	$\displaystyle\texttt{\#}\;\langle\textrm{NonHashLineChar}\rangle\;\langle\textrm{REST\_OF\_LINE}\rangle$
$\displaystyle\langle\textrm{SUBHEAD}\rangle$	$\displaystyle::=$	$\displaystyle\texttt{\#\#}\;\langle\textrm{REST\_OF\_LINE}\rangle$
$\displaystyle\langle\textrm{SIGIL}\rangle$	$\displaystyle::=$	$\displaystyle\texttt{\textasciitilde{}example}\;\langle\textrm{NewLine}\rangle$
		$\displaystyle\;\mid\;\texttt{\textasciitilde{}run}\;\langle\textrm{NewLine}\rangle$
		$\displaystyle\;\mid\;\texttt{\textasciitilde{}run on{-}load}\;\langle\textrm{NewLine}\rangle$

Figure 3. Notlob grammar - Terminals. Grammar listing.

Priority	Terminals
20	SEPARATOR , TESTS_HEAD , BINDING_HEAD , REFERENCES_HEAD , APPENDIX_HEAD
10	MOD_HEAD , SUBHEAD , SIGIL , TEST_SIGIL
8	INDENTED_LINE , BLANK , BULLET
5	REF
1	LINE_START_TEXT , PROSE_TEXT (fallback)

Table 1. Notlob terminal priorities.

Command	Description
run	Assemble and execute a .lob file
test	Run all claims in a .lob file, or the whole project
build	Assemble a .lob file (or the whole project) to source artifacts
weave	Render a .lob file (or the whole project) as Markdown
graph	Export the package name-graph (JSON or Turtle RDF)
query	Query the package name-graph

Table 2. Command Overview for the Notlob Toolchain.

AI Coding Agents

AI coding agents use language models and software tools to plan, edit, test, and maintain code with varying levels of autonomy.

See all 329 papers

LLM-as-Code: Agentic Programming for Agent Harness
Jun 14, 2026Junjia Qi, Zichuan Fu, Jingtong Gao +4AI Agent Reliability LLM Agent Orchestration
City University of Hong Kong · Tencent Jarvis Lab
$λ_A$ : A Typed Lambda Calculus for LLM Agent Composition
Apr 13, 2026Qin LiuLLM Agents LLM Agent Orchestration
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China · Software Institute, Nanjing University, Nanjing, Jiangsu, China
Libra: Training the Environment for Agentic Information Retrieval
May 26, 2026Xuan Zhao, Andy Chiu, Gengyu WangAI Coding Agents Code Localization
Salesforce

Jun 14, 2026J/K move · Enter open · S save

LLM-as-Code: Agentic Programming for Agent Harness

Junjia Qi, Zichuan Fu, Jingtong Gao, Wenlin Zhang+3

City University of Hong Kong · Tencent Jarvis Lab

AI Agent Reliability LLM Agent Orchestration Long-Horizon LLM Agents LLM Agent Reliability

Open paper AskPDF arXiv

Every major LLM agent framework gives the LLM the role of orchestrator; the model decides what to do next, when to call tools, and when to stop. We argue that token explosion, control-flow hallucination, and unreliable completion are not implementation bugs but architectural consequences of assigning the deterministic work of looping, branching, and sequencing to a probabilistic system. A better prompt or a stronger model cannot guarantee the reliability of the LLM agent. We therefore propose Agentic Programming, in which the program governs all control flow, and the LLM is itself part of it, an adaptive component we call LLM-as-Code and invoke only where a task calls for reasoning or generation. Within each call the model keeps full flexibility, but it cannot alter the program's execution path. With control in the program, the LLM's context is built from the execution history's call tree and forms a directed acyclic graph (DAG). Each call's context length is then determined by its call depth rather than by accumulation over steps. A case study of computer-use agents shows that the design is practical, not just a theoretical stance, substantially improving the stability of long visual operation sequences.

Abstract

AI Coding Agents

Explore similar work

LLM-as-Code: Agentic Programming for Agent Harness

λAλ_AλA​: A Typed Lambda Calculus for LLM Agent Composition

Libra: Training the Environment for Agentic Information Retrieval

$λ_A$ : A Typed Lambda Calculus for LLM Agent Composition