 |
International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
|
Issue: June 2026
Volume 11 | Issue 6
Review Result and Publication of Paper within : 2-3 days
Click Here For more DetailsFor Authors
Forms / Download
Published Issue Details
Editorial Board
Other IMP Links
Facts & Figure
Impact Factor : 8.14
Issue per Year : 12
Volume Published : 11
Issue Published : 121
Article Submitted : 24737
Article Published : 9361
Total Authors : 24875
Total Reviewer : 861
Total Countries : 169
Indexing Partner
Licence
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
Published Paper Details
|
|
| Paper Title: | ATLAS: A Dual-Mode Multi-Agent Architecture for AI Code Assistance That Balances Developer Productivity and Skill Development |
| Authors Name: | Gautam Jhalaria , Laxmi Verma , Mahi Uboweja , Sujal Sen , Narendra Dewangan |
| Download E-Certificate: | Download |
| Author Reg. ID: |
IJRTI_212591
|
| Published Paper Id: | IJRTI2605090 |
| Published In: | Volume 11 Issue 5, May-2026 |
| DOI: | |
| Abstract: | Coding assistants powered by artificial intelligence (AI) have become very popular, with more than 90% of professional developers saying they use them regularly by 2026. Recent empirical evidence indicates a fundamental tension: tools that enhance productivity via autonomous code generation may lead to cognitive offloading and skill atrophy, resulting in developers achieving 17% lower scores on conceptual mastery assessments [1]. Conversely, tools that emphasize learning through scaffolded guidance compromise development speed. The ”productivity-learning paradox” is another way to show this tension. A randomized controlled trial showed that developers are objectively 19% slower with AI tools, even though they think they are 20% faster [2]. This paper introduces ATLAS (Adaptive Teaching and Learning Assistant for Software), a dual-mode AI code assistant that integrates autonomous code generation (Build mode) and Socratic mentoring (Mentor mode) within a unified multi-agent architecture. In build mode, a cyclical LangGraph StateGraph of specialized agents—Architect, Planner, Developer, and Reviewer—automatically creates, checks, and applies code patches. In Mentor mode, the same Retrieval-Augmented Generation (RAG) context pipeline is used, but it uses a different five-agent topology (with roles like Skeptic, Pedagogue, and Mentor) to stop solutions from leaking. It limits tool access to read-only operations and replaces direct code generation with scaffolded dialogue, which is enforced at the architecture level with smooth state recovery. Both modes use the same context engineering pipeline, which puts together system prompts, retrieved code context, active file state, and conversation history in real time. ATLAS is evaluated through a within-subjects user study with 48 participants completing 4 programming tasks in both modes. Results demonstrate that Build mode reduces end-to-end task resolution time by 43.1% compared to unassisted development (p < 0.001), while Mentor mode improves conceptual understanding scores by 48.2% compared to Build mode (p < 0.001). 75% of participants expressed a preference for the ability to switch between modes based on task complexity. The contributions of this paper are threefold: (1) a formal dual-mode architecture with server-side enforcement that prevents pedagogical guardrail bypassing, (2) a shared context engineering pipeline that adapts retrieval and prompt assembly per interaction mode, and (3) empirical evidence supporting the efficacy of bimodal AI assistance in addressing the productivity-learning paradox. |
| Keywords: | AI Code Assistant, Multi-Agent Systems, Large Language Models, Socratic Tutoring, Software Engineering, Dual-Mode Architecture, Retrieval-Augmented Generation. |
| Cite Article: | "ATLAS: A Dual-Mode Multi-Agent Architecture for AI Code Assistance That Balances Developer Productivity and Skill Development", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 5, page no.a723-a730, May-2026, Available :http://www.ijrti.org/papers/IJRTI2605090.pdf |
| Downloads: | 000122 |
| ISSN: |
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016 An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator |
| Publication Details: |
Published Paper ID: IJRTI2605090
Registration ID:212591
Published In: Volume 11 Issue 5, May-2026
DOI (Digital Object Identifier):
Page No: a723-a730 Country: Raipur, Chhatisgarh, India Research Area: Engineering Publisher : IJ Publication Published Paper URL : https://www.ijrti.org/viewpaperforall?paper=IJRTI2605090 Published Paper PDF: https://www.ijrti.org/papers/IJRTI2605090 |
| Share Article: | |
|
Click Here to Download This Article |
|
| Article Preview | |
|
|
|
Major Indexing from www.ijrti.org
| Google Scholar | ResearcherID Thomson Reuters | Mendeley : reference manager | Academia.edu |
| arXiv.org : cornell university library | Research Gate | CiteSeerX | DOAJ : Directory of Open Access Journals |
| DRJI | Index Copernicus International | Scribd | DocStoc |
ISSN Details
 |
 |
|
ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED,
Journal Starting Year (ESTD) : 2016
DOI (A digital object identifier)
| Providing A digital object identifier by DOI.ONE How to Get DOI? |
Conference
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Important Details
Join RMS/Earn 300
WhatsApp
Click Here
Click Here
Indexing Partner |
|||
| Copyright © 2026 - All Rights Reserved - IJRTI | |||