arXiv · 2611.20759
Instant Weight-Space Consolidation for Long-Term Memory in LLMs
Abstract
Agentic memory systems give LLMs persistent memory by extracting experience into text and retrieving it at query time, but the model itself does not evolve: however many interactions it has had, it starts each query the same. Extraction errors compound, implicit cross-session patterns that no single fragment states cannot be surfaced, and the construction cost grows with every conversation. Fine-tuning on past interactions does change the weights, but requires backpropagation at serving time and degrades on long histories. We introduce CLAM (Carried Latent Adapter Memory), which combines the strengths of both: a recurrent hypernetwork performs parametric consolidation, compiling a stream of session activations into a low-rank adapter in a single forward pass with no gradient steps and no language-model generation calls, while a complementary episodic buffer supplies verbatim detail at inference. A gated latent state carries knowledge across sessions in fixed size, so the parametric memory accumulates without growing. On LoCoMo and LongMemEval-S across three open models (2-7B parameters), CLAM leads all agentic baselines by 1-45 points and all gradient-based parametric methods by 10-45 points, while requiring zero generative LLM calls, zero gradient steps, and 3-151x less wall-clock time than extraction systems to build its memory. The two channels are complementary: the consolidated adapter adds 12-15 accuracy points when the episodic buffer misses the gold evidence, and still adds 4-5 points even with an oracle buffer.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Manan Suri, Dinesh Manocha. 2026-11-16. Instant Weight-Space Consolidation for Long-Term Memory in LLMs. https://searcharxiv.com/abs/2611.20759
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.