Camyla: Scaling Autonomous Research in Medical Image Segmentation
Summary: arXiv:2604.10696v1 Announce Type: new
Abstract: We present Camyla, a system for fully autonomous research within the scientific domain of medical image segmentation. Camyla transforms raw datasets into literature-grounded research proposals, executable experiments, and complete manuscripts without human intervention.
Autonomous experimentation over long horizons poses three interrelated challenges:
- Search effort drifts toward unpromising directions.
- Knowledge from earlier trials degrades as context accumulates.
- Recovery from failures collapses into repetitive incremental fixes.
To address these challenges, the system combines three coupled mechanisms:
- Quality-Weighted Branch Exploration: This mechanism allocates effort across competing proposals to ensure effective exploration of viable options.
- Layered Reflective Memory: This feature retains and compresses cross-trial knowledge at multiple granularities, enabling better learning from past experiments.
- Divergent Diagnostic Feedback: This mechanism diversifies recovery strategies after underperforming trials, preventing stagnation in progress.
The system is evaluated on CamylaBench, a contamination-free benchmark of 31 datasets constructed exclusively from 2025 publications, under a strict zero-intervention protocol across two independent runs within a total of 28 days on an 8-GPU cluster.
Across the two runs, Camyla generates more than 2,700 novel model implementations and 40 complete manuscripts. It surpasses the strongest per-dataset baseline selected from 14 established architectures, including nnU-Net, on 22 and 18 of 31 datasets under identical training budgets, respectively (union: 24/31).
Senior human reviewers score the generated manuscripts at the T1/T2 boundary of contemporary medical imaging journals. Relative to automated baselines, Camyla outperforms AutoML and NAS systems on aggregate segmentation performance and exceeds six open-ended research agents on both task completion and baseline-surpassing frequency.
These results suggest that domain-scale autonomous research is achievable in medical image segmentation. The implications of this research are profound, as it opens up new avenues for efficiency and innovation in the field of medical imaging, potentially leading to faster and more accurate diagnostic tools.