ConvMem: Convolutional Memory for Long-Context Reasoning

TL;DR - ConvMem is a training-free framework for long-context LLM reasoning that hierarchically summarizes text segments using a parallel, convolution-inspired process. It reduces sequential reasoning depth from linear to logarithmic while outperforming training-free baselines on two multi-hop QA benchmarks.

• Treats a query-prompted LLM as a convolutional kernel that summarizes context segments in a hierarchical tree.
• Uses configurable strides and skip connections to preserve and propagate evidence while limiting error accumulation.
• Applies multiple kernels to split complex queries into distinct semantic reasoning channels.
• Enables parallel processing across context segments and reasoning threads without costly reinforcement learning.