Mergeable Model-Side Aggregation States for Long-Context Language Models

Overview

arXiv:2607.26448v1 Announce Type: new Abstract: A known limitation of long-context language models is their increasingly unreliable performance in non-additive, set-based aggregation as context length grows. Examples include cardinality estimation, set relationships, and grouped statistics, which widely exist in logs, program outputs, tables, and multi-turn conversations. To provide the aggregation state required by these tasks, we introduce a model-side aggregation interface that maintains comp

SpinGraph analysis pending — check back after processing.