Overview
Field: NLP / AI for Science Authors: Bobo Li, Hao Fei, Tianjie Ju, Mong-Li Lee, Wynne Hsu Published: 2026-08-13 arXiv: 2608.13558
Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depends. Existing systems typically reason over text, code, labels, or precomputed summaries, leaving scientifically decisive spatial, temporal, cross-channel, and procedural relations unavailable to the agent.
Key Contributions
- OmniScientist: an end-to-end, omni-modal AI scientist that conducts multidisciplinary research directly from heterogeneous raw evidence.
- A perception layer plus 3 autonomous agents (ideation, experiment, writeup) operate within a deterministic pipeline, allowing observations to shape research questions, experimental decisions, and final claims throughout the research lifecycle.
- Code-based idea, rigour, and claim checks enforce novelty screening, statistical validity, execution provenance, and numerical traceability.
- Tested on 36 real-data cases spanning 5 discipline families, 4 families of scientific evidence, and modalities including images, signals, audio, video, 3-D structures, trajectories, tables, formulae, and graphs.
- The system completed the full path from raw data to compiled manuscript in all 36 cases, achieving a mean overall paper score of 6.3 with the reference reasoning backbone.
- In paired comparisons against a blind variant receiving only precomputed scalar features, direct perception improved all 7 evaluation dimensions and won 85% of head-to-head judgments.
Evaluation
Conclusion
These results show that lifecycle-wide perception is essential for evidence-grounded scientific discovery and provide a practical path toward broadly capable AI scientists.
--- *Auto-collected on 2026-08-15.*