AutoViewMem Reorganizes Conversational Memory into Self-Configuring Semantic Views
AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory
Builders running memory-augmented agents on open Qwen3 models can adopt this approach, since it beat strong memory baselines on LoCoMo and PersonaMem without adding retrieval routing or iterative search.
A paper on arXiv (2609.21940) introduces AutoViewMem, a data-driven framework that organizes an LLM agent's long-term conversational memory into self-configuring, low-overlap semantic views before indexing. The framework discovers candidate views from interaction traces and moves semantic disentanglement to write time, letting standard top-K similarity search retrieve focused evidence without explicit routing or iterative retrieval. On the LoCoMo and PersonaMem benchmarks, AutoViewMem improves long-horizon question answering and personalization over strong memory baselines with both Qwen3-8B and Qwen3-14B backbones. Offline consolidation in AutoViewMem further improves memory compactness and consistency while preserving a simple inference pipeline.
AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory
Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing memory systems typically rely on fixed granularities or static schemas, but these designs struggle when heterogeneous information, such as preferences, events, constraints, and temporal updates, is embedded in a single mixed representation. The resulting semantic interference makes top-K retrieval sensitive to noise and often leaves relevant evidence poorly ranked. We present AutoViewMem, a data-driven framework that organizes long-term conversational memory into self-configuring, low-overlap semantic views before indexing. AutoViewMem discovers candidate views from interaction traces, selects a compact complementary view set, and uses these views to guide write-time structured extraction of provenance-grounded memories. This representation-first design moves semantic disentanglement from retrieval time to write time, allowing standard top-K similarity search to retrieve focused evidence without explicit routing or iterative retrieval. We further apply offline consolidation to improve memory compactness and consistency. Experiments on the LoCoMo and PersonaMem benchmarks, under both Qwen3-8B and Qwen3-14B backbones, show that AutoViewMem improves long-horizon question answering and personalization over strong memory baselines while preserving a simple inference pipeline.