CCoR: Reasoning-Aware Context Compression via Submodular Information Gain

Context compression has emerged as a promising paradigm to reduce high computational costs and redundant noise in Large Language Models (LLMs) across data-intensive scenarios. Existing methods span task-agnostic and task-aware approaches. Task-agnostic methods sacrifice fine-grained details by operating independently of downstream queries, whereas current task-aware paradigms remain strictly query-centric. Consequently, only text semantically relevant to the query is selectively retained, inadvertently discarding critical logical scaffolding required for multi-step derivations. In this work, we propose **CCoR** (**C**ontext **C**ompression f**o**r **R**easoning), a novel framework that preserves essential reasoning evidence rather than relying solely on query semantic relevance. Specifically, CCoR formulates context importance evaluation as a submodular maximization problem to rigorously capture sufficiency and necessity for model reasoning. Building upon this, CCoR introduces an adaptive compression mechanism that preserves high-importance chunks into distinct representations while condensing redundant content into latent summaries, optimized jointly via supervised alignment and reasoning-preservation reinforcement learning. Extensive experiments show that CCoR substantially outperforms existing baselines, achieving robust reasoning preservation under stringent compression rates. Notably, under $8\times$ compression, CCoR achieves an average 9.23% F1 gain over state-of-the-art (SOTA) across three long-context benchmarks using LLaMA-3.1-8B-Instruct.