Home / Current Issue / Paper 1716344
Agentic Language Model (ALM): A Task-Centric Framework for Autonomous AI Systems
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence
DOI: https://doi.org/10.64388/IREV9I10-1716344
Abstract
Large Language Models (LLMs) have significantly advanced natural language processing, yet they remain limited in executing structured, real-world tasks autonomously. This paper introduces the Agentic Language Model (ALM), a novel AI paradigm developed by RecoilLife TenseAI that shifts intelligence from token prediction to task execution. ALM is built upon the Agentic Reinforced Operational Workflow (AROW) and trained using Per Agentic Task (PAT) units, representing complete task lifecycles. With a dataset of approximately 1.8 million PATs, ALM demonstrates improved task completion accuracy, reduced hallucination, and enhanced decision-making. This work presents the architecture, training methodology, evaluation, and future implications of ALM as a foundation for autonomous AI systems.
Keywords
Agentic AI, Autonomous Systems, Task Execution, Reinforcement Learning, Language Models, Workflow Intelligence
How to cite this paper
@article{1716344,
author = {Ayush Maurya, Deependra B. Maurya},
title = {Agentic Language Model (ALM): A Task-Centric Framework for Autonomous AI Systems},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {1774-1777},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1716344.pdf},
abstract = {Large Language Models (LLMs) have significantly advanced natural language processing, yet they remain limited in executing structured, real-world tasks autonomously. This paper introduces the Agentic Language Model (ALM), a novel AI paradigm developed by RecoilLife TenseAI that shifts intelligence from token prediction to task execution. ALM is built upon the Agentic Reinforced Operational Workflow (AROW) and trained using Per Agentic Task (PAT) units, representing complete task lifecycles. With a dataset of approximately 1.8 million PATs, ALM demonstrates improved task completion accuracy, reduced hallucination, and enhanced decision-making. This work presents the architecture, training methodology, evaluation, and future implications of ALM as a foundation for autonomous AI systems.},
keywords = {Agentic AI, Autonomous Systems, Task Execution, Reinforcement Learning, Language Models, Workflow Intelligence},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1716344}
}