Unverified50% confidenceFactExact time
METTA decomposes the fast adaptation phase into two time scales: causal neural memory handles fine-grained within-episode adaptation and runs with linear sequence complexity, while compact episode-level summaries support cross-episode long-horizon task inference.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe model design incorporates temporal convolution blocks and temporal attention mechanisms to enhance inter-frame consistency.70% similarUnverifiedThe Spaced Repetition algorithm combats forgetting by scientifically scheduling review intervals and is the core mechanism of memory tools such as Anki68% similarUnverifiedThe adaptive agent memory system adopts a dual-store structure: the fast layer is an append-only episodic log (preserving immutable evidence), the slow layer is semantic/procedural storage that consolidates recurring content, and migration between the two layers is determined by measured future utility.68% similarUnverifiedEngineering approaches to solving character drift include periodically re-injecting character profile summaries, performing character consistency checks on outputs, and internalizing specific characters in the model through fine-tuning.67% similarUnverifiedIn long-cycle tasks, asynchronous mode can significantly reduce overall execution time, while synchronous mode ensures result correctness when logic is strictly sequential; the two modes can be used in combination.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088282API
curl https://kongchang.com/api/v1/knowledge/claims/1088282MCP
get_claim(id=1088282)