MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agents

Researchers introduced MemoryForge, a framework that synthesizes lifelong autobiographical memory from brief target personas to make frozen Large Language Models (LLMs) exhibit more human-like behaviors in role-play and user simulation. In experiments on PersonaGym and SimulatorArena, MemoryForge outperformed strong descriptive conditioning baselines across multiple metrics and LLM backbones, according to the arXiv paper 2608.00007v1.

arXiv:2608.00007v1 Announce Type: new Abstract: Equipping Large Language Models LLMs with human-like personas is crucial for agentic applications, such as role-play and user simulation. Traditional prompt-based methods rely on descriptive conditioning by injecting static textual profiles, which often makes agents show generic behaviors due to a lack of realistic life memory. To fill this gap, we introduce memory-based conditioning, a paradigm inspired by the cognitive psychology, which replaces abstract profiles with an autobiographical memory base, enabling frozen LLMs to dynamically retrieve situation-relevant memory to guide their behaviors. We formalize its enabling task as customized lifelong memory synthesis and propose MemoryForge, a novel framework to synthesize such lifelong memory from brief target personas. MemoryForge has three key components: a context generator for socio-historical grounding, a life organizer for developmental coherence toward the target identity, and a multi-resolution simulator that balances broad temporal summaries with high-fidelity episodic experiences. Experiments on PersonaGym for role-play and SimulatorArena for user-simulation, show that the synthesized memory base by MemoryForge enables frozen LLMs to exhibit more human-like behaviors than strong descriptive conditioning baselines across multiple metrics and LLM backbones.