Agentic Discovery with Active Hypothesis Exploration for Visual Recognition
For researchers in neural architecture search, this work introduces a novel paradigm that combines LLM-driven hypothesis generation with evolutionary branching to discover lightweight vision architectures.
HypoExplore is an agentic framework that discovers neural architectures for visual recognition by treating it as hypothesis-driven scientific inquiry. It achieved 94.11% accuracy on CIFAR-10, evolving from 18.91%, and generalized to CIFAR-100, Tiny-ImageNet, and MedMNIST with state-of-the-art results.
We introduce HypoExplore, an agentic framework that formulates neural architecture discovery for visual recognition as a hypothesis-driven scientific inquiry. Given a human-specified high-level research direction, HypoExplore ideates, implements, evaluates, and improves neural architectures through evolutionary branching. New hypotheses are created using a large language model by selecting a parent hypothesis to build upon, guided by a dual strategy that balances exploiting validated principles with resolving uncertain ones. Our proposed framework maintains a Trajectory Tree that records the lineage of all proposed architectures, and a Hypothesis Memory Bank that actively tracks confidence scores acquired through experimental evidence. After each experiment, multiple feedback agents analyze the results from different perspectives and consolidate their findings into hypothesis confidence updates. Our framework is tested on discovering lightweight vision architectures on CIFAR-10, with the best achieving 94.11% accuracy evolved from a root node baseline that starts at 18.91%, and generalizes to CIFAR-100 and Tiny-ImageNet. We further demonstrate applicability to a specialized domain by conducting independent architecture discovery runs on MedMNIST, which yield a state-of-the-art performance. We show that hypothesis confidence scores grow increasingly predictive as evidence accumulates, and that the learned principles transfer across independent evolutionary lineages, suggesting that HypoExplore not only discovers stronger architectures, but can help build a genuine understanding of the design space.