Consolidation Without Weights: What the Complementary Learning Systems Analogy Licenses in LLM Agent Memory, and Why the Systems That Borrow Its Name Do Not Inherit Its Guarantee
Abstract
Life of Research
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0.
Memory systems for language-model agents almost all contain a step called consolidation, and almost all of them cite, or gesture at, the complementary learning systems account of hippocampus and neocortex when they name it. In that account consolidation is a specific operation: repeated replay from a fast, sparsely coded store into a slow learner whose shared parameters change, which is what produces generalisation to material never stored and which is also where interference lives. This paper separates what that theory commits its borrower to from what agent memory systems actually do. Four commitments are stated and used as an audit instrument. Against them, deployed agent memory divides into two families and neither instantiates the mechanism, for opposite reasons. The larger, textual family changes no parameters at all: its consolidation is iterated LLM-authored rewriting of an external store, and a 2026 controlled study reports that iterating it drives utility up and then down, in their setting below the no-memory baseline, while no replay result located here reports falling below its own no-replay control. A smaller parametric family, which appeared during 2026 and falsifies the common claim that agent memory never touches weights, does change parameters, but most of it buys stability through per-task adapter isolation or expandable blocks, and isolation withholds the shared representation that the source theory identifies as the common cause of interference and generalisation alike. The paper argues that the field's avoidance of online parametric transfer is well supported by evidence about what such transfer costs, and that what is not supported is retaining the vocabulary while declining the mechanism. It states the five measurements that would decide the question and identifies the single published configuration whose shape matches the theory.
Questions about this paper
Who wrote "Consolidation Without Weights"?
Pranay Mahendrakar wrote "Consolidation Without Weights: What the Complementary Learning Systems Analogy Licenses in LLM Agent Memory, and Why the Systems That Borrow Its Name Do Not Inherit Its Guarantee", published 11 Sep 2026. Pranay Mahendrakar is an Indian AI specialist and LLM engineer based in Bengaluru, India. He is the Managing Director of SonyTech, Nodal Coordinator at IIRS-ISRO, and an instructor at Tutorials Point. His work covers large language models, natural language processing, computer vision and retrieval-augmented generation. He publishes open-access research papers and is the author of three books: Just AI With Pranay, Multiverse of AI and It's Me LLM.
Is "Consolidation Without Weights" free to read?
Yes. "Consolidation Without Weights" by Pranay Mahendrakar is open access under a Creative Commons Attribution 4.0 licence, with the full PDF available from Zenodo at https://doi.org/10.5281/zenodo.22699102. There is no paywall and no account required.
How do I cite "Consolidation Without Weights"?
Cite the DOI: Mahendrakar, P. (2026). Consolidation Without Weights: What the Complementary Learning Systems Analogy Licenses in LLM Agent Memory, and Why the Systems That Borrow Its Name Do Not Inherit Its Guarantee. Zenodo. https://doi.org/10.5281/zenodo.22699102 A BibTeX entry is provided on this page.