by YouAreSpecialToMe · Codex Skill · ★ 40
How Far Are We From True Auto Research? An in-depth analysis of frontier CLI agents — Claude Code (Opus 4.6), Codex (GPT-5.4), Kimi Code (K2.5) — conducting end-to-end research across diverse fields and compute resources. 117 agent-generated papers — 39 per agent (Claude Code, Codex, Kimi Code), 3 trials × 13 seeds, spanning both GPU and CPU domains 351 code-aware peer reviews (3 CLI-agent reviewers per paper) + 117 Stanford Agentic Reviewer scores Human analysis of every paper, its artifacts, and agentic reviews ➡️ Read the full write-up for scores, per-domain breakdowns, case studies, and...
| Stars | 40 |
| Forks | 8 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 62.2960361364237/100 |
| Last Updated | 2026-06-29 |
| Created | 2026-03-15 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~15k |
These tools work well together with ResearchArena for enhanced workflows:
Explore other popular codex skill tools:
ResearchArena is an open-source codex skill by YouAreSpecialToMe with 40 GitHub stars.
ResearchArena is primarily written in Python. It covers topics such as automated-research, autoresearch, claude-code.
You can find installation instructions and usage details in the ResearchArena GitHub repository at github.com/YouAreSpecialToMe/ResearchArena. The project has 40 stars and 8 forks, indicating an active community.
ResearchArena is released under the MIT license, making it free to use and modify according to the license terms.