International Journal on Science and Technology

E-ISSN: 2229-7677   •   Impact Factor: 9.88

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 17 Issue 2 April-June 2026 Submit your research before last 3 days of June to publish your research paper in the issue of April-June.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 17 Issue 2
April-June 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Multi-Agent Legal Document Reasoning with Multimodal Evidence

Author(s) Mrs Varalakshmi Madda, Ms. vijitha Katroth, Mr. Imran Mohammed
Country India
Abstract Despite increasing use of large language models to aid analysis of legal documents, current systems often generate responses that are not grounded in the source contract, resulting in hallucinations, omissions or misinterpretations of obligations, and low user trust in LegalTech solutions that require guaranteed traceability and accuracy. Most current pipelines either retrieve context on a paragraph or higher level, or use general-purpose semantic search, which are inadequate for high clause-density, rigid legal documents. Critical clauses may be skipped or the passages retrieved are insufficient to provide a direct answer.
Furthermore, a pipeline doesn't guarantee the last response is derived solely from retrieved passages and the generation process may still introduce additional assumptions and knowledge. These problems would get worse when handling multiple documents with diverse formats, paragraph numbering standards, and legal drafting conventions, where retrieval reliability and consistency decreases and error rates grow cumulatively. To tackle these limitations, we propose a novel clause-aware, multi-agent pipeline which partitions documents into clause-level units, retrieves and ranks clauses with dynamic and dynamic clause weighting per query, and conditions generation solely on retrieved clauses. Our proposed method guarantees evidence-backed and traceable responses and increases consistency over documents and decreases unsupported responses against state-of-the-art baselines.
Keywords Legal Document Analysis, Semantic Search, Multi-Agent Systems, Natural Language Processing, Vector Embeddings, Conversational AI, ChatGPT, Information Retrieval, Artificial Intelligence, Document Intelligence
Field Engineering
Published In Volume 17, Issue 2, April-June 2026
Published On 2026-04-30
DOI https://doi.org/10.71097/IJSAT.v17.i2.10961
View / Download PDF File

Share this


CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 17 Isu 1Cover Page Vol 16 Isu 3Cover Page Vol 16 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJSAT
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us Message on WhatsApp +91-9687-182-185 editor@ijsat.org