R0049/2026-03-31/Q001-SRC05 — Scorecard¶
Source¶
| Title | Agent Laboratory: Using LLMs as Research Assistants |
| Publisher | GitHub / Academic paper |
| Authors | Samuel Schmidgall et al. |
| Date | 2024-2025 |
| URL | https://github.com/SamuelSchmidgall/AgentLaboratory |
| Type | Open-source software with academic paper |
Ratings¶
| Dimension | Rating |
|---|---|
| Reliability | Medium-High |
| Relevance | Medium |
| Missing data | Low risk |
| Measurement | Low risk |
| Selective reporting | Low risk |
| Randomization | N/A |
| Protocol deviation | N/A |
| COI/funding | Low risk |
Rationale¶
| Dimension | Rationale |
|---|---|
| Reliability | Open-source with academic publication; MIT licensed; active development |
| Relevance | Automates research workflow but without analytical rigor mechanisms — relevant as a near-miss for Q001 |
| Measurement | Published evaluation metrics for research output quality |
Evidence Extracts¶
| Evidence | Summary |
|---|---|
| SRC05-E01 | Agent Laboratory automates three research phases but lacks formal analytical rigor mechanisms |