TRUST Agents: A Collaborative Multi-Agent Framework for Fake News Detection, Explainable Verification, and Logic-Aware Claim Reasoning

TL;DR

TRUST Agents is a multi-agent framework designed for explainable fake news detection, claim verification, and reasoning, emphasizing interpretability and evidence transparency over raw accuracy.

Contribution

It introduces a collaborative multi-agent system with specialized components for claim extraction, evidence retrieval, verification, and explanation, including extensions for complex claim decomposition and logical reasoning.

Findings

Improves interpretability and evidence transparency in fact verification.

Outperforms baseline models in explainability and reasoning on LIAR benchmark.

Highlights retrieval quality and uncertainty calibration as key challenges.

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.