PulseAugur
EN
LIVE 08:35:09

New MARQ system boosts LLM requirement quality assessment with SE knowledge

By PulseAugur Editorial · [1 sources] ·

Researchers have developed MARQ, a novel system designed to improve the quality assessment of requirements for large language models (LLMs). By integrating expert-derived systems engineering knowledge, MARQ aims to enhance the accuracy and consistency of LLM-based evaluations. Testing MARQ with Claude Opus-5, GPT-5.6 "Sol", and Gemma-3-12B on a NASA dataset showed significant improvements, particularly for Claude Opus-5, which achieved a median F1 score of 0.80. AI

IMPACT Enhances LLM capabilities in requirement engineering, potentially improving system development outcomes.

RANK_REASON The cluster describes a research paper detailing a new system and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New MARQ system boosts LLM requirement quality assessment with SE knowledge

How we ranked this

Signal score
18 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a research paper detailing a new system and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Jannatul Shefa, Alejandro Salado, Paul Wach, Taylan G. Topcu ·

    MARQ: A Modular, LLM-Agnostic Requirement Quality Assessor Infused with Systems Engineering Knowledge

    arXiv:2610.36234v1 Announce Type: new Abstract: Requirements engineering (RE) is foundational to systems engineering (SE), as requirement defects can propagate downstream and adversely affect development outcomes. Although large language models (LLMs) are promising for requiremen…

RELATED ENTITIES

RELATED TOPICS