Beyond Inference-Only Deployment: Comparing Weight-Based Consolidation Against Cascading Compaction 事件

Beyond Inference-Only Deployment: Comparing Weight-Based Consolidation Against Cascading Compaction arXiv:2605.24657v1 Announce Type: new Abstract: Major LLM platforms deploy models in an inference-only configuration: the model serves requests but never updates per-user weights. Users must repeatedly re-teach preferences, corrections, and project context, and context-based workarounds consume context-window space and degrade under cascading compaction. We evaluate an alternative: nightly consol