GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory

GraphMemix introduces a combinatorial‑optimization graph memory framework that organizes long‑term multimodal agent memory as query‑aware evidence forests. It constructs candidate graphs by expanding seed memories through schema and semantic relations, then decouples evidence utility from anchor‑conditioned relation verification to reduce redundancy, and finally optimizes a forest‑format memory context within a maximum evidence budget. Experiments on four benchmarks show significant accuracy gains and a new Pareto frontier between accuracy and lifecycle cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

• rag
• agents
• multimodal
• benchmarks