We present Cognitive Loop via In-Situ Optimization (CLIO), an agent that couples a continuously-updated belief-state graph with a recursive plan-then-act loop. The result is a reasoning agent that can contribute something qualitatively different, which we term \emph{calibrated deference}: the capacity to recognize when its own tools or assumptions are failing, to adapt its strategy in response, and to generate mechanistic hypotheses that guide experimental revision. We tested CLIO in a closed-loop human-AI campaign to design an aqueous organic redox flow battery (AORFB) negolyte, with CLIO leading proposal and interpretation in close partnership with chemists who synthesized, characterized, and weighed in on design choices. Across 17 candidates over three rounds, CLIO converged on a top phosphonate candidate; characterization confirmed a 130~mV improvement in redox potential over the literature baseline. Characterization then revealed unexpectedly poor electrochemical reversibility -- a regression no property predictor had flagged. CLIO generated competing mechanistic hypotheses, prioritized discriminating diagnostics, traced the failure to phosphonate-potassium ion pairing, and prescribed a sulfonate replacement. The resulting compound showed substantially improved electrochemical reversibility and maintained a 90~mV improvement in redox potential, closing the design-make-test-redesign loop.

翻译：我们提出了基于原位优化的认知环路（CLIO），该智能体将持续更新的信念状态图与递归式"规划-行动"循环相结合。由此产生的推理智能体能够实现一种性质不同的能力，我们称之为"校准鉴别"：即识别自身工具或假设失效的时刻，据此调整策略，并生成指导实验修正的机理假说。我们在人机协同闭环研究中测试了CLIO，目标是设计水系有机氧化还原液流电池（AORFB）的负极电解液，CLIO主导提案与解释工作，与负责合成、表征及设计决策的化学家紧密合作。经过三轮17个候选分子的迭代，CLIO收敛于最优膦酸酯候选物；表征结果显示其氧化还原电位较文献基准提升130~mV。后续表征意外揭示其电化学可逆性显著缺陷——这一逆向指标未被任何性质预测模型捕捉。CLIO生成竞争性机理假说，优先区分诊断方案，将失效归因于膦酸酯-钾离子配对效应，并提出磺酸基团替代方案。最终合成的化合物在保持90~mV氧化还原电位提升的同时，电化学可逆性得到显著改善，完整实现了设计-制造-测试-再设计的闭环迭代。