# Knowledge Access Beats Model Size: Memory Augmented Routing for Persistent AI Agents

arXiv: https://arxiv.org/abs/2603.23013 · HTML: https://mlsanity.com/paper/2603.23013/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [AutoMix: Automatically Mixing Language Models](https://mlsanity.com/paper/2310.12963/) (2023)
- [A Unified Approach to Routing and Cascading for LLMs](https://mlsanity.com/paper/2410.10347/) (2024)
- [Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression](https://mlsanity.com/paper/2310.15594/) (2023)
- [A Plan Reuse Mechanism for LLM-Driven Agent](https://mlsanity.com/paper/2512.21309/) (2025)

## Abstract (arXiv)

Production AI agents frequently receive user-specific queries that are highly repetitive, with up to 47% being semantically similar to prior interactions, yet each query is typically processed with the same computational cost. We argue that this redundancy can be exploited through conversational memory, transforming repetition from a cost burden into an efficiency advantage. We propose a memory-augmented inference framework in which a lightweight 8B-parameter model leverages retrieved conversational context to answer all queries via a low-cost inference path. Without any additional training or labeled data, this approach achieves 30.5% F1, recovering 69% of the performance of a full-context 235B model while reducing effective cost by 96%. Notably, a 235B model without memory (13.7% F1) underperforms even the standalone 8B model (15.4% F1), indicating that for user-specific queries, access to relevant knowledge outweighs model scale. We further analyze the role of routing and confidence. At practical confidence thresholds, routing alone already directs 96% of queries to the small model, but yields poor accuracy (13.0% F1) due to confident hallucinations. Memory does not substantially alter routing decisions; instead, it improves correctness by grounding responses in retrieved user-specific information. As conversational memory accumulates over time, coverage of recurring topics increases, further narrowing the performance gap. We evaluate on 152 LoCoMo questions (Qwen3-8B/235B) and 500 LongMemEval questions. Incorporating hybrid retrieval (BM25 + cosine similarity) improves performance by an additional +7.7 F1, demonstrating that retrieval quality directly enhances end-to-end system performance. Overall, our results highlight that memory, rather than model size, is the primary driver of accuracy and efficiency in persistent AI agents.