English

Cognis: Context-Aware Memory for Conversational AI Agents

Computation and Language 2026-04-23 v1 Artificial Intelligence Information Retrieval

Abstract

LLM agents lack persistent memory, causing conversations to reset each session and preventing personalization over time. We present Lyzr Cognis, a unified memory architecture for conversational AI agents that addresses this limitation through a multi-stage retrieval pipeline. Cognis combines a dual-store backend pairing OpenSearch BM25 keyword matching with Matryoshka vector similarity search, fused via Reciprocal Rank Fusion. Its context-aware ingestion pipeline retrieves existing memories before extraction, enabling intelligent version tracking that preserves full memory history while keeping the store consistent. Temporal boosting enhances time-sensitive queries, and a BGE-2 cross-encoder reranker refines final result quality. We evaluate Cognis on two independent benchmarks -- LoCoMo and LongMemEval -- across eight answer generation models, demonstrating state-of-the-art performance on both. The system is open-source and deployed in production serving conversational AI applications.

Keywords

Cite

@article{arxiv.2604.19771,
  title  = {Cognis: Context-Aware Memory for Conversational AI Agents},
  author = {Parshva Daftari and Khush Patel and Shreyas Kapale and Jithin George and Siva Surendira},
  journal= {arXiv preprint arXiv:2604.19771},
  year   = {2026}
}

Comments

30 pages, 8 figures, 11 tables

R2 v1 2026-07-01T12:28:58.258Z