analiza aiqbench
CLIO demonstrates a novel "calibrated deference" capability, allowing an AI agent to detect its own predictive failures and generate mechanistic hypotheses to guide experimental revisions. In a closed-loop campaign for battery design, the system successfully identified a specific ion-pairing failure missed by standard regression models and prescribed a chemical replacement that restored electrochemical reversibility. This approach validates the utility of recursive plan-then-act loops for bridging the gap between computational prediction and physical reality in scientific discovery.
Closed-Loop Molecular Design with Calibrated Deference
arXiv:2606.02618v1 Announce Type: cross Abstract: 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.
Authors:Newman Cheng, Gordon Broadbent IV, Jason Dong, Syed Mohammed Ali Hussaini, Farman Ullah, Morris Sharp, Gabrielle Barnes, Nanlin Guo, Deyu Zou, Karin Strauss, William Chappell, David G. Kwabi, Bichlien H. Nguyen, Jake A. Smith
Abstract: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.
Computational Engineering, Finance, and Science (cs.CE); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Chemical Physics (physics.chem-ph)
arXiv:2606.02618 [cs.CE]
(or arXiv:2606.02618v1 [cs.CE] for this version)
Text integral sub licența deschisă a publicației · 240 cuvinte