arXiv AI By Saad Alqithami

Endogenous Information in Routing Games: Memory-Constrained Equilibria, Recall Braess Paradoxes, and Memory Design

Read the original on arXiv AI →

The paper investigates routing games where travelers choose routes based on remembered or surfaced alternatives rather than a fixed set of actions. It introduces a tractable design theory for endogenous recall, linking a finite‑memory micro model—where each traveler updates a memory state via a logit rule and policies like LRU—to a stationary salience model that assigns route‑specific weights. The authors prove existence and uniqueness of a Forgetful Wardrop Equilibrium, develop algorithms for network design under budget constraints, and identify a Recall Braess Paradox where better recall can worsen equilibrium delay.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Jul 10

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

arXiv:2607. 08032v1 Announce Type: new Abstract: Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions.

By Ashwin Gerard Colaco, Nada Lahjouji
Hugging Face Trending Papers
Jun 29

Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management

We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces. Instead of treating Low-Rank Adaptation (LoRA) modules as disposable per-task adapters, NSR manages them as compressible, retrievable memory units on a frozen backbone through a recurring cycle: (1) compress learned LoRAs via SVD, (2) reserve them in a TaskKnowledgeBank, (3) recall related past LoRAs by embedding similarity to warm-start new or returning tasks, and (4) reallocate the active subspace accordingly, with distillation protecting prior tasks.