paper-with-me

Papers

Trust-Aware Multi-Agent Traceability: Confidence-Calibrated Knowledge Graphs for Consistent Software Artifact Management

2026-06-15 · Mohamed Essam, Kareem Wael, Azza Hassan, Ahmed Haitham, Mahmoud Soliman, Samer Saber, Ibrahim Habib arxiv

Multi-agent AI systems are increasingly used to automate software engineering tasks including requirements analysis, architecture design, test generation, and traceability linking. When these agents operate as a sequential pipeline over shared software artifacts, errors and low-confidence decisions made by upstream agents propagate to downstream stages, producing orphaned requirements, contradictory links, and compliance gaps that pose significant risks in safety-critical domains. We propose a trust-aware coordination framework where a shared knowledge graph serves as both centralized semantic memory and a coordination surface through which agents assess and build upon each other's contributions using calibrated confidence scores. Our approach introduces a two-stage traceability link prediction pipeline combining embedding-based retrieval with LLM-based multi-criteria analysis, a traceability seeding mechanism that enables comparison between derivation-time and validation-time confidence, and a consistency protocol governing pipeline interactions through confidence threshold gating, confidence divergence detection, and conflict resolution. We evaluate on an automotive software engineering case study measuring link prediction calibration, protocol effectiveness, threshold sensitivity, and the impact of traceability seeding. Ablation studies confirm that confidence calibration is essential for effective pipeline coordination.

📄 PDF Abstract BibTeX arXiv:2606.17203

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge GraphsLink Prediction

Similar Papers 제목 키워드 기반

Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based Reasoning

2025-07-09 · Konstantinos I. Roumeliotis, Ranjan Sapkota, Manoj Karkee, Nikolaos D. Tselikas

Modern Artificial Intelligence (AI) increasingly relies on multi-agent architectures that blend visual and language understanding. Yet, a pressing challenge remains: How can we trust these agents especially in zero-shot …

BenchmarkingImage RetrievalOptical Character Recognition (OCR)RAG+3

Trustworthy Agents for Electronic Health Records through Confidence Estimation

2025-08-26 · Yongwoo Song, Minbyul Jeong, Mujeen Sung arxiv

Large language models (LLMs) show promise for extracting information from Electronic Health Records (EHR) and supporting clinical decisions. However, deployment in clinical settings faces challenges due to hallucination …

Question Answering

Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization

2026-06-16 · Aueaphum Aueawatthanaphisut, Badri Raj Lamichhane arxiv

Big-Data-as-a-Service (BDaaS) platforms require re liable automation across data ingestion, cleaning, feature engi neering, model development, deployment, and post-deployment monitoring. However, existing LLM-based data …

Feature Engineering

Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents

2026-05-18 · Sanderson Oliveira de Macedo, Ronaldo Martins da Costa arxiv

Legacy systems concentrate business rules, architectural decisions, and operational exceptions that often remain implicit in code, data, configuration, and maintenance practices. At the same time, language-model-based co…

Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs

2026-04-17 · Eren Unlu arxiv

As large language models (LLMs) transition into autonomous agents integrated with extensive tool ecosystems, traditional routing heuristics increasingly succumb to context pollution and "overthinking". We argue that the …