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

• URL: http://arxiv.org/abs/2606.17203v1
• Date: Mon, 15 Jun 2026 18:41:50 GMT
• Title: Trust-Aware Multi-Agent Traceability: Confidence-Calibrated Knowledge Graphs for Consistent Software Artifact Management
• Abstract summary: In software engineering, multi-agent AI systems are increasingly used to automate requirements analysis, architecture design, test generation, and traceability linking.<n>We propose a trust-aware coordination framework where a shared knowledge graph serves as both centralized semantic memory and a coordination surface.<n>We evaluate on an automotive software engineering case study measuring link prediction calibration, protocol effectiveness, threshold sensitivity, and the impact of traceability seeding.
• Score: 0.7329200485567826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents [75.69180947909148]
  We propose a trajectory-level UQ framework for large language model (LLM) agents.<n>RuPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges.<n>We evaluate RUPA on representative agent benchmarks, including $$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families.
  arXiv  Detail & Related papers  (2026-08-17T01:40:14Z)
• Uncertainty-Aware Deepfake Detection via Multi-View Structural Learning [6.951909224842812]
  Security-critical biometric and forensic applications require accurate predictions and reliable confidence estimates, particularly under distribution shift.<n>We propose an uncertainty-aware deepfake detection framework that identifies manipulations through inconsistencies across complementary evidence sources.<n>We introduce Inter-Branch Disagreement (IBDC), a disagreement-aware uncertainty modeling mechanism that links predictive uncertainty to conflicts among evidence streams.
  arXiv  Detail & Related papers  (2026-07-30T18:42:01Z)
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development [0.3670422696827525]
  UA-ChatDev is an uncertainty-aware multi-agent software development framework.<n>It integrates uncertainty quantification into agent interactions.<n>It consistently outperforms existing single-agent and multi-agent software development frameworks.
  arXiv  Detail & Related papers  (2026-07-02T13:56:57Z)
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security [57.35851886874902]
  Agentic AI systems execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness.<n>This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments.<n>For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies.
  arXiv  Detail & Related papers  (2026-05-17T10:26:37Z)
• Process Supervision of Confidence Margin for Calibrated LLM Reasoning [52.373121066425455]
  Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability.<n>Yet, outcome-based reward often incentivizes models to be overconfident, leading to hallucinations, unreliable confidence-based control, and unnecessary compute allocation.<n>We introduce Reinforcement Learning with Confidence Margin (textbfRLCM), a calibration-aware RL framework that jointly optimize correctness and confidence reliability.
  arXiv  Detail & Related papers  (2026-04-25T14:40:13Z)
• Statistical-Based Metric Threshold Setting Method for Software Fault Prediction in Firmware Projects: An Industrial Experience [4.339839287869652]
  Machine learning-based fault prediction models have demonstrated high accuracy, but their lack of interpretability limits their adoption in industrial settings.<n>We present a structured process for defining context-specific software metric thresholds suitable for integration into fault detection in industrial settings.<n>Our approach supports cross-project fault prediction by deriving thresholds from one set of projects and applying them to independently developed firmware.
  arXiv  Detail & Related papers  (2026-02-06T16:19:36Z)
• PaTAS: A Parallel System for Trust Propagation in Neural Networks Using Subjective Logic [1.8485970721272895]
  This paper introduces the Parallel Trust Assessment System (PaTAS), a framework for modeling and propagating trust in neural networks.<n>Experiments on real-world and adversarial datasets demonstrate that PaTAS produces interpretable, symmetric, and convergent trust estimates.
  arXiv  Detail & Related papers  (2025-11-25T18:15:36Z)
• Semantic Chain-of-Trust: Autonomous Trust Orchestration for Collaborator Selection via Hypergraph-Aided Agentic AI [57.58120823855315]
  This paper proposes an autonomous trust orchestration method based on a new concept of semantic chain-of-trust.<n>Our technique employs agentic AI and hypergraph to establish and maintain trust relationships among devices.<n> Experimental results demonstrate that the proposed method achieves resource-efficient trust evaluation.
  arXiv  Detail & Related papers  (2025-07-31T13:53:25Z)
• Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
  We propose a unified backdoor detection framework in the semi-honest setting.<n>Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.<n> Notably, it is the first to effectively detect backdoors in multimodal large language models.
  arXiv  Detail & Related papers  (2025-03-21T06:12:06Z)
• Bayesian Methods for Trust in Collaborative Multi-Agent Autonomy [11.246557832016238]
  In safety-critical and contested environments, adversaries may infiltrate and compromise a number of agents. We analyze state of the art multi-target tracking algorithms under this compromised agent threat model. We design a trust estimation framework using hierarchical Bayesian updating.
  arXiv  Detail & Related papers  (2024-03-25T17:17:35Z)
• A Factor Graph Model of Trust for a Collaborative Multi-Agent System [8.286807697708113]
  Trust is the reliance and confidence an agent has in the information, behaviors, intentions, truthfulness, and capabilities of others within the system. This paper introduces a new graphical approach that utilizes factor graphs to represent the interdependent behaviors and trustworthiness among agents. Our method for evaluating trust is decentralized and considers key interdependent sub-factors such as proximity safety, consistency, and cooperation.
  arXiv  Detail & Related papers  (2024-02-10T21:44:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.