Unverified50% confidenceSolutionExact time
The paper proposes addressing agents stalling due to accumulated history through periodic forgetting (periodically discarding the search state, including each agent's session records and full candidate solution history, then restarting the search from the current best candidate).
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGradient-based methods often overwrite old knowledge when learning new tasks, causing catastrophic forgetting, whereas population-based evolutionary systems naturally maintain an archive of solution diversity.72% similarUnverifiedIf the memory store is full of duplicate, outdated, or mutually contradictory entries, the retrieval results will contain large amounts of low-value information, crowding out context space and even misleading the model, which is context pollution.70% similarVerifiedCatastrophic Forgetting is a classic pain point for neural networks in continual learning scenarios, where updating parameters on new tasks overwrites the weight distribution corresponding to old tasks, causing degradation of previously learned capabilities69% similarUnverifiedRegression tasks require predicting continuous fine-grained numerical values and rely on fine-grained sample information in the history, which is lost when compressed into a compact persona description.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032784API
curl https://kongchang.com/api/v1/knowledge/claims/1032784MCP
get_claim(id=1032784)