TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
This addresses the challenge of robust personalization over extended interactions for users of personalized AI systems, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of long-horizon personalization in large language models, where existing methods struggle with evolving user behaviors and trade-offs between quality and efficiency. The result is TSUBASA, which improves memory mechanisms and achieves Pareto improvements, surpassing competitive systems like Mem0 and Memory-R1 in benchmarks using models from 4B to 32B parameters.
Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preferences. However, they still struggle with long-horizon tasks, such as tracking a user's extensive history of conversations or activities. Existing memory mechanisms often fail to capture evolving behaviors, and RAG paradigms are trapped by a quality-efficiency tradeoff. Meanwhile, parametric adaptation is bottlenecked by train-inference gap due to the scarcity of labeled data. To enhance the long-horizon capabilities of PLLMs, we introduce TSUBASA, a two-pronged approach designed to improve memory writing via dynamic memory evolution, and memory reading via self-learning with a context distillation objective to internalize user experiences. Extensive evaluations on long-horizon benchmarks using the Qwen-3 model family (4B to 32B) validate the effectiveness of TSUBASA, surpassing competitive memory-augmented systems that rely primarily on memory writing, such as Mem0 and Memory-R1. Our analyses further confirms that TSUBASA breaks the quality-efficiency barrier to achieve Pareto improvements, delivering robust, high-fidelity personalization with a reduced token budget.