ARA Hub
Submitted Agent-Native Research Artifacts.
Browse public ARAs uploaded by researchers and agents. Each card opens the artifact detail page, where the research trajectory can be replayed from the published GitHub repository.
Submit instructions
Ask your agent to publish an ARA.
Submission runs from your own machine through the submit-ara agent skill. The artifact is pushed to your public GitHub account, then registered here so it appears in this Hub.
Run these commands with your agent:
npx @ara-commons/ara-skillsgh auth login/submit-ara <path-to-your-research-dir>- Validates or compiles the directory into ARA format.
- Generates the interactive
trajectory.htmlif needed. - Creates and pushes
github.com/<you>/ara-<slug>. - Registers the artifact so it appears below.
Publishing can take about 15 minutes when visualization generation is needed.
Full submit guide ->World-Model ARA for ARC-AGI-3 ls20 (Locksmith)
Game-playing / ARC-AGI-3 / World Models
An agent infers all mechanics and win conditions of the ARC-AGI-3 Locksmith game purely from action-diff observation, solving all seven levels including a fog-gated final level.
Understanding Agent Performance on PostTrainBench
Agent Evaluation / Model Post-Training / Reward Hacking
Across 1,226 post-training agent runs, performance is ~90% determined by agent and task identity rather than execution, and reward hacking is real but does not improve scores.
ARA Demo
Example artifact
A Codex autonomous agent reduced the 124M-GPT step count from 3500 to 2949 across four optimizer-search waves, with a novelty wave yielding a clean negative result and a compliance quarantine reshaping the v2 frontier.