MemoryAthena: Adaptive Routing over Latent and Generated Memories

arXiv:2609.25853 · cs.CL · Submitted 2026-09-22 · Read on arXiv

cs.CL

Submitted: 2026-09-22

Updated: 2026-09-26

Code: https://github.com/OLAResearch/ATHENA

Project page: https://olaresearch.org/MemoryATHENA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Perplexity — 14× in this paper · explained in 3 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Adaptation — 9× in this paper · explained in 1 episode
• AGN — 7× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• RAG — 4× in this paper · explained in 3 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Latent Representation — 3× in this paper · explained in 2 episodes
• Natural Questions — 3× in this paper
• Aggregation — 2× in this paper · explained in 1 episode
• F1 Score — 2× in this paper · explained in 3 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Causal Inference — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes

Sources

• Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
• Mistral 7B
• Frozen Memory Is Not Enough: Rethinking External Memory as Extraction
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• MLP Memory: A Retriever-Pretrained Memory for Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering