# Agentic Discovery with Active Hypothesis Exploration for Visual Recognition

arXiv: https://arxiv.org/abs/2604.12999 · HTML: https://mlsanity.com/paper/2604.12999/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 64 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 6 of 6)

- [MedMamba: Vision Mamba for Medical Image Classification](https://mlsanity.com/paper/2403.03849/) (2024)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [Towards Execution-Grounded Automated AI Research](https://mlsanity.com/paper/2601.14525/) (2026)
- [MARS: Modular Agent with Reflective Search for Automated AI Research](https://mlsanity.com/paper/2602.02660/) (2026)
- [Neural Architecture Discovery via Autonomous Evolution](https://mlsanity.com/paper/2507.18074/) (2025)
- [Language Modeling by Language Models](https://mlsanity.com/paper/2506.20249/) (2025)

## Built on by (most cited first, 1 of 1)

- [SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm](https://mlsanity.com/paper/2610.20431/) (2026)

## Abstract (arXiv)

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.