Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory
This addresses the challenge of long-term memory and temporal reasoning in conversational agents, which is crucial for applications like personal assistants, but it is incremental as it builds on existing memory systems with structured retrieval methods.
The paper tackles the problem of conversational AI agents struggling with temporally grounded facts and preferences over long-term interactions by introducing Chronos, a temporal-aware memory framework that decomposes dialogue into structured events and uses dynamic prompting for retrieval, achieving up to 95.60% accuracy on a benchmark, a 7.67% improvement over prior systems.
Recent advances in Large Language Models (LLMs) have enabled conversational AI agents to engage in extended multi-turn interactions spanning weeks or months. However, existing memory systems struggle to reason over temporally grounded facts and preferences that evolve across months of interaction and lack effective retrieval strategies for multi-hop, time-sensitive queries over long dialogue histories. We introduce Chronos, a novel temporal-aware memory framework that decomposes raw dialogue into subject-verb-object event tuples with resolved datetime ranges and entity aliases, indexing them in a structured event calendar alongside a turn calendar that preserves full conversational context. At query time, Chronos applies dynamic prompting to generate tailored retrieval guidance for each question, directing the agent on what to retrieve, how to filter across time ranges, and how to approach multi-hop reasoning through an iterative tool-calling loop over both calendars. We evaluate Chronos with 8 LLMs, both open-source and closed-source, on the LongMemEvalS benchmark comprising 500 questions spanning six categories of dialogue history tasks. Chronos Low achieves 92.60% and Chronos High scores 95.60% accuracy, setting a new state of the art with an improvement of 7.67% over the best prior system. Ablation results reveal the events calendar accounts for a 58.9% gain on the baseline while all other components yield improvements between 15.5% and 22.3%. Notably, Chronos Low alone surpasses prior approaches evaluated under their strongest model configurations.