Developing Adaptive Context Compression Techniques for Large Language Models (LLMs) in Long-Running Interactions

ArXi:2603.29193v1 Announce Type: cross Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression framework that integrates importance-aware memory selection, coherence-sensitive filtering, and dynamic budget allocation to retain essential conversational information while controlling context growth.