[
    {
        "id": "osp-15484",
        "type": "article-journal",
        "title": "Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems",
        "author": [
            {
                "family": "Zhang",
                "given": "Tunyu"
            },
            {
                "family": "Zhao",
                "given": "Zihao"
            },
            {
                "family": "Zhao",
                "given": "Yusong"
            },
            {
                "family": "Shi",
                "given": "Haizhou"
            },
            {
                "family": "Li",
                "given": "Zhuohang"
            },
            {
                "family": "Chen",
                "given": "Haoxian"
            },
            {
                "family": "Wang",
                "given": "Hao"
            },
            {
                "family": "Metaxas",
                "given": "Dimitris N."
            }
        ],
        "URL": "https://omanscience.com/en/articles/sequential-probabilistic-uncertainty-estimation-for-parallel-multi-agent-reasoning-systems",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "LLM-based multi-agent systems (MAS) have attracted growing attention for improving reasoning through interaction among multiple agents. In this work, we focus on parallel multi-agent reasoning systems, where several agents solve the same problem over multiple rounds and aggregate their outputs into a final answer. Despite their strong reasoning performance, uncertainty estimation for such systems remains underexplored: the reliability of a MAS depends not only on individual generations, but also on how agents interact and evolve across rounds. We propose SAUCE (Sequential Agent Uncertainty through Consensus Evolution), a lightweight, training-free uncertainty estimator that formulates MAS uncertainty as sequential inference over a latent system-level belief. SAUCE aggregates round-level agreement and generation-uncertainty signals through a filtering-style update. Across five backbones, five benchmarks, and two MAS protocols, SAUCE improves misclassification detection, selective prediction, and calibration over a broad set of uncertainty estimation baselines, including standard log-likelihood-based methods and MAS-specific estimators."
    }
]