DORA AI Scientist: Multi-agent Virtual Research Team for Scientific Exploration Discovery and Automated Report Generation
Bibliographic record
Abstract
Abstract Modern goal-oriented scientific research process involves hierarchical teams of researchers of diverse backgrounds performing generalist and domain-specific tasks. Many of these tasks include hypothesis generation, literature review, data collection, cleanup, processing and analysis, experimental design, virtual and physical experiments, research report and academic paper writing, reference management, bibliography and quality control. Most of these tasks can be performed automatically or in a co-pilot mode by the generative reinforcement learning systems. In this paper, we introduce a versatile multi-agent scientific exploration and draft outline research assistant (DORA), which provides multiple templates and workflows for automated or semi-automated research studies and report generation. Under user guidance, it employs hierarchical teams of AI agents based on the plug-and-play generalist and domain-specific large language models (LLMs) exploiting a variety of specialized research tools and open data repositories and generates high-quality research outputs publication drafts with maximally-accurate references. DORA is designed to minimize the time and effort required for manuscript preparation, thereby enabling researchers to devote more attention to high-value discovery tasks. The system is constantly evolving with user feedback with regular feature and resource updates. The platform is available at https://dora.insilico.com .
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.013 | 0.008 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".