# Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences

arXiv: https://arxiv.org/abs/2509.16189 · HTML: https://mlsanity.com/paper/2509.16189/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 88 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Data Distributional Properties Drive Emergent In-Context Learning in Transformers](https://mlsanity.com/paper/2205.05055/) (2022)
- [Stabilizing Transformers for Reinforcement Learning](https://mlsanity.com/paper/1910.06764/) (2019)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [Taken out of context: On measuring situational awareness in LLMs](https://mlsanity.com/paper/2309.00667/) (2023)
- [Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models](https://mlsanity.com/paper/2310.10378/) (2023)
- [Test-Time Training on Nearest Neighbors for Large Language Models](https://mlsanity.com/paper/2305.18466/) (2023)
- [Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs](https://mlsanity.com/paper/2403.19827/) (2024)
- [Relating transformers to models and neural representations of the hippocampal formation](https://mlsanity.com/paper/2112.04035/) (2021)
- [Grounded Language Learning Fast and Slow](https://mlsanity.com/paper/2009.01719/) (2020)
- [Retrieval-Augmented Reinforcement Learning](https://mlsanity.com/paper/2202.08417/) (2022)
- [Grokking of Hierarchical Structure in Vanilla Transformers](https://mlsanity.com/paper/2305.18741/) (2023)
- [Transformers generalize differently from information stored in context vs in weights](https://mlsanity.com/paper/2210.05675/) (2022)
- [Reasoning to Learn from Latent Thoughts](https://mlsanity.com/paper/2503.18866/) (2025)
- [Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs](https://mlsanity.com/paper/2410.08020/) (2024)
- [Towards mental time travel: a hierarchical memory for reinforcement learning agents](https://mlsanity.com/paper/2105.14039/) (2021)
- [On the generalization of language models from in-context learning and finetuning: a controlled study](https://mlsanity.com/paper/2505.00661/) (2025)
- [The broader spectrum of in-context learning](https://mlsanity.com/paper/2412.03782/) (2024)
- [ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer](https://mlsanity.com/paper/2502.21228/) (2025)

## Built on by (most cited first, 15 of 15)

- [Learning Next Action Predictors from Human-Computer Interaction](https://mlsanity.com/paper/2603.05923/) (2026)
- [Contextual Agentic Memory is a Memo, Not True Memory](https://mlsanity.com/paper/2604.27707/) (2026)
- [Do Language Models Track Entities Across State Changes?](https://mlsanity.com/paper/2605.30233/) (2026)
- [Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs](https://mlsanity.com/paper/2512.06258/) (2025)
- [ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay](https://mlsanity.com/paper/2511.19033/) (2025)
- [Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management](https://mlsanity.com/paper/2512.21567/) (2025)
- [HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering](https://mlsanity.com/paper/2602.15513/) (2026)
- [Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents](https://mlsanity.com/paper/2606.11680/) (2026)
- [Revolutionizing Long-Term Memory in AI: New Horizons with High-Capacity and High-Speed Storage](https://mlsanity.com/paper/2602.16192/) (2026)
- [Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG](https://mlsanity.com/paper/2603.23562/) (2026)
- [SRAG: RAG with Structured Data Improves Vector Retrieval](https://mlsanity.com/paper/2603.26670/) (2026)
- [Factorization Regret mediates compositional generalization in latent space](https://mlsanity.com/paper/2603.27134/) (2026)
- [Improving Latent Generalization Using Test-time Compute](https://mlsanity.com/paper/2604.01430/) (2026)
- [The Illusion of Latent Generalization: Bi-directionality and the Reversal Curse](https://mlsanity.com/paper/2604.04943/) (2026)
- [Does Episodic Memory Help Close the Lexical Frequency Gap in Sensitivity to Syntactic Contrasts? A Test Using Retrieval-Augmented Language Models](https://mlsanity.com/paper/2608.23851/) (2026)

## Abstract (arXiv)

When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weakness of parametric machine learning systems is their failure to exhibit latent learning -- learning information that is not relevant to the task at hand, but that might be useful in a future task. We show how this perspective links failures ranging from the reversal curse in language modeling to new findings on agent-based navigation. We then highlight how cognitive science points to episodic memory as a potential part of the solution to these issues. Correspondingly, we show that a system with an oracle retrieval mechanism can use learning experiences more flexibly to generalize better across many of these challenges. We also identify some of the essential components for effectively using retrieval, including the importance of within-example in-context learning for acquiring the ability to use information across retrieved examples. In summary, our results illustrate one possible contributor to the relative data inefficiency of current machine learning systems compared to natural intelligence, and help to understand how retrieval methods can complement parametric learning to improve generalization. We close by discussing some of the links between these findings and prior results in cognitive science and neuroscience, and the broader implications.