Retrieval-Augmented Generation (RAG) systems are susceptible to factual inconsistencies when retrieved evidence is conflicting, a common issue with open-domain sources. Prevailing multi-agent approaches attempt to resolve this through unstructured debates that treat all information sources as equally credible. Concurrently, reliability-aware systems address source quality but typically only as a weighting factor during final aggregation, failing to integrate this crucial signal into the reasoning process itself. This paper proposes DARE (A Dialectical Adversarial RAG Engine), a novel framework that implements a structured dialectical process to resolve such conflicts through an evidence-aware adversarial agent that initiates a structured cross-examination of claims made by other agents. This process forces each claim to be defended against the complete set of source documents, allowing the system to dynamically infer an argument’s credibility based on its logical resilience. By organizing the debate as a structured dialectic, DARE provides a more robust and systematic framework for synthesizing truth from unreliable and conflicting information. Empirical experiments across three challenging benchmarks show that DARE consistently outperforms strong baselines, achieving performance gains of up to 77%.