Towards Unified Memory Adaptation for LLM Agents: Textual, Latent, and Parametric Pathways

Equipping large language models (LLMs) with external memory banks is a critical stepping stone towards autonomous agents. Current approaches have concentrated substantial efforts on the design of memory construction and retrieval mechanisms. However, they typically relegate memory utilization to the simplistic concatenation of explicit texts for LLM inputs, thereby remaining constrained by the fundamental bottlenecks of context overload and semantic dilution. In response to this dilemma, we present UniMem, a unified memory adaptation framework that empowers LLM agents to holistically harness memory information, extending beyond textual signals into latent and parametric dimensions. Operating along these pathways, UniMem not only elevates contextual density through latent compression, but also facilitates semantic grounding via parametric modulation. Extensive experiments show that UniMem (I) achieves superior performance across diverse benchmarks, including long-term dialogue, memory personalization, and open-domain question answering; and (II) can seamlessly complement prevailing memory construction and retrieval mechanisms for synergistic enhancements.