SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation
Imported from official source
Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with agent-side events such as session stop and start, crons, and memory consolidation. …
This version
- Version
- 1 of 1
- Recorded
- September 30, 2026 22:00
- Change
- Initial
- Content hash
92ea6c0e5082317e2080cf2cd239dca7- All versions
- Revision history