Introducing LLMScript: A Turing Complete Prompt Based Scripting Language for LLMs with No External Coding Required

LLMScript is a Turing complete scripting language that runs entirely inside the LLM with no external coding required. It can orchestrate AI calls with control structures (loops, recursion, variables, functions, and decision-making), you can create workflows that leverage AI in dynamic, and interactive ways by capturing the results of AI calls and user inputs then make decisions using iterative workflows to create custom AI solutions. It enables a systematic way of integrating Chain of Thought (CoT), Tree of Thought (ToT), and Graph of Thought (GoT) reasoning and others into your workflow; this means you can build AI-driven solutions that integrate multi-step reasoning, iterative exploration, and even decision trees that dynamically shift based on intermediate results. It empowers users to systematically interact with an LLM to create innovative AI solutions.

Authors

Institutions

Publication Details

Published
2024-11-26
DOI
https://doi.org/10.1109/fllm63129.2024.10852477
Primary Topic
Library Science and Information Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Introducing LLMScript: A Turing Complete Prompt Based Scripting Language for LLMs with No External Coding Required

Shahin Mowzoon, Mishkin Faustini
Library Science and Information Systems
article

Introducing LLMScript: A Turing Complete Prompt Based Scripting Language for LLMs with No External Coding Required

Shahin Mowzoon, Mishkin Faustini
article en

Abstract

LLMScript is a Turing complete scripting language that runs entirely inside the LLM with no external coding required. It can orchestrate AI calls with control structures (loops, recursion, variables, functions, and decision-making), you can create workflows that leverage AI in dynamic, and interactive ways by capturing the results of AI calls and user inputs then make decisions using iterative workflows to create custom AI solutions. It enables a systematic way of integrating Chain of Thought (CoT), Tree of Thought (ToT), and Graph of Thought (GoT) reasoning and others into your workflow; this means you can build AI-driven solutions that integrate multi-step reasoning, iterative exploration, and even decision trees that dynamically shift based on intermediate results. It empowers users to systematically interact with an LLM to create innovative AI solutions.

Harvard University Press (US)
Openalex Percentile: Top 58%
Library Science and Information Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.