Multi-Agent Claim Verification

A multi-agent framework for automated fact-checking and claim verification at scale.

Venue: ICWSM 2026

We develop a multi-agent pipeline that decomposes complex claim verification into subtasks handled by specialized agents — including evidence retrieval, stance detection, and verdict aggregation. The system is designed to scale to real-world misinformation detection scenarios.

Key contributions:

  • Modular multi-agent architecture for end-to-end claim verification
  • Evaluation on benchmark fact-checking datasets
  • Analysis of agent collaboration and failure modes