# FindingNEMO

- **Event:** [The Recursive Agents Hackathon](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon)
- **When:** Sat, Oct 17 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Artur Lima](https://cerebralvalley.ai/u/artur), [Luiz Barbosa](https://cerebralvalley.ai/u/lfpmb), [Carolina Bartunek](https://cerebralvalley.ai/u/cbartunek)
- **GitHub:** https://github.com/LuizFelipeBarbosa/schema-voyager
- **Demo video:** https://www.loom.com/share/d33fdb90fa48472ea4b32b966958cb1b
- **Gallery:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/88

LLM agents learn can learn skills from action sequences that worked before. But a skill doesn't know why it worked, so when the world changes, the agent replays it and fails again and again. FindingNEMO learns verified rules in training. When the world contradicts one, it notices at the exact step, revises with a single LLM call, and recovers in the same episode, where a skill-only agent keeps repeating the mistake.

## More from The Recursive Agents Hackathon

- [Zen](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/85)
- [Capy](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/86)
- [The last harness](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/87)
- [Alchemist](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/89)
- [Tornado](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/90)
- [Habedevs](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/91)

---

Markdown version of https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/88. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt