MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment

arXiv:2601.22361v2 Announce Type: replace-cross Abstract: Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial progress in automated veracity assessment, including automated fact-checking and claim verification systems. Typical veracity assessment pipelines break down complex claims into sub-claims, retrieve external evidence, and then apply LLM reasoning to assess veracity. However, existing methods often treat evidence retrieval as a static, isolated step and do not effectively manage or reuse retrieved evidence across claims. In this work, we propose MERMAID, a memory-enhanced multi-agent veracity assessment framework that tightly couples the retrieval and reasoning processes. MERMAID integrates agent-driven search, structured knowledge representations, and a persistent memory module within a Reason-Action style iterative process, enabling dynamic evidence acquisition and cross-claim evidence reuse. By retaining retrieved evidence in an evidence memory, the framework reduces redundant searches and improves verification efficiency and consistency. We evaluate MERMAID on three fact-checking benchmarks and two claim-verification datasets using multiple LLMs, including GPT, LLaMA, and Qwen families. Experimental results show that MERMAID achieves state-of-the-art performance while improving the search efficiency, demonstrating the effectiveness of synergizing retrieval, reasoning, and memory for reliable veracity assessment.

Related

• Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation
• KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning
• Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
• Council Mode: Mitigating Hallucination and Bias in LLMs via Multi-Agent Consensus
• Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks

Source: arXiv cs.AI | 2026-04-14