Large language models (LLM) suffer from various forms of biases due to the biased data sets used to train the models. At the same time, human cognitive biases have an equal propensity to express themselves when using LLMs for software engineering tasks. Software testing is a critical phase of the software development life cycle. Confirmation bias is reported to have deteriorated software testing by designing more specification-consistent test cases compared to specification-inconsistent test cases. However, there is a lack of debiasing (mitigation) strategies in this regard. In this paper, we initially present preliminary experimental evidence for the manifestation of confirmation bias by an LLM - Chat-GPT4.0 in the designing of functional test cases. Subsequently, we present a vision for debiasing confirmation bias in functional software testing by leveraging LLMs via a multi-agent approach. The proposed vision may improve the performance of LLMs in terms of reduced confirmation bias and serve as a debiasing technique for functional software testing.