ClaimVerAgents: A Multi-Agent Retrieval-Augmented Claim Verification Framework
Bibliographic record
Abstract
The spread of fake news has had major impact on public discourse and trust. Detection methods rely heavily on evidence quality and verdict accuracy. Traditional approaches, often based on static sources, struggle with outdated or incomplete information, especially for new or obscure claims. Large Language Models (LLMs) offer promising reasoning and generation capabilities but face similar challenges, including outdated knowledge and limited coverage. To address these challenges, we present ClaimVerAgents1, a novel, retrieval-augmented, modular, and interpretable multi-agent system that leverages LLMs for real-time fake news verification. Each autonomous agent fulfills a specialized sub-task: claim extraction, query generation, evidence evaluation, verdict decision, and explanation generation, all within a transparent, confidenceaware pipeline. Extensive experiments on the PolitiFact dataset show that ClaimVerAgents outperforms both classical and LLM-based baselines in accuracy and robustness. Importantly, the system generates structured, humanreadable explanations alongside its verdicts, enhancing trust and interpretability.1Code and data are available at https://anonymous.4open.science/r/ ClaimVerAgents-832E
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".