TRUST Agents: A Collaborative Multi-Agent Framework for Fake News Detection, Explainable Verification, and Logic-Aware Claim Reasoning
Gautama Shastry Bulusu Venkata, Santhosh Kakarla, Maheedhar Omtri Mohan, Aishwarya Gaddam
Why It Matters
What makes this one worth your time
This paper addresses the critical issue of fake news detection by improving the transparency and reasoning processes involved in fact verification, which is essential for building trust in automated systems.
TRUST Agents offers a novel approach to fact verification through a multi-agent framework.
Summary
The TRUST Agents framework introduces a collaborative multi-agent system for fake news detection and explainable verification, enhancing interpretability and reasoning capabilities while addressing the limitations of traditional supervised models.
Key contributions
- Introduction of a multi-agent framework that improves explainability and reasoning in fact verification tasks.
Notable insights
- The integration of a decomposer agent and a multi-agent jury enhances the system's ability to handle complex claims effectively.
Possible limitations
- The reliance on retrieval quality and uncertainty calibration remains a significant challenge for achieving fully trustworthy automated verification.
Abstract
arXiv:2604.12184v1 Announce Type: new Abstract: TRUST Agents is a collaborative multi-agent framework for explainable fact verification and fake news detection. Rather than treating verification as a simple true-or-false classification task, the system identifies verifiable claims, retrieves relevant evidence, compares claims against that evidence, reasons under uncertainty, and generates explanations that humans can inspect. The baseline pipeline consists of four specialized agents. A claim extractor uses named entity recognition, dependency parsing, and LLM-based extraction to identify factual claims. A retrieval agent performs hybrid sparse and dense search using BM25 and FAISS. A verifier agent compares claims with retrieved evidence and produces verdicts with calibrated confidence. An explainer agent then generates a human-readable report with explicit evidence citations. To handle complex claims more effectively, we introduce a research-oriented extension with three additional components: a decomposer agent inspired by LoCal-style claim decomposition, a Delphi-inspired multi-agent jury with specialized verifier personas, and a logic aggregator that combines atomic verdicts using conjunction, disjunction, negation, and implication. We evaluate both pipelines on the LIAR benchmark against fine-tuned BERT, fine-tuned RoBERTa, and a zero-shot LLM baseline. Although supervised encoders remain stronger on raw metrics, TRUST Agents improves interpretability, evidence transparency, and reasoning over compound claims. Results also show that retrieval quality and uncertainty calibration remain the main bottlenecks in trustworthy automated fact verification.