In LLM agents, memory routing circuits emerge at 0.6B scale while content circuits appear only at 4B, and write/read operations recruit a pre-existing late-layer context hub instead of creating a new one, enabling a 76% accurate unsupervised failure diagnostic.
GitHub repository , howpublished =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
TSAG lets LLMs use external tools for financial time series analysis, with a new benchmark showing capable agents achieve near-perfect tool accuracy and minimal hallucination.
citing papers explorer
-
What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis
In LLM agents, memory routing circuits emerge at 0.6B scale while content circuits appear only at 4B, and write/read operations recruit a pre-existing late-layer context hub instead of creating a new one, enabling a 76% accurate unsupervised failure diagnostic.
-
Time Series Augmented Generation for Financial Applications
TSAG lets LLMs use external tools for financial time series analysis, with a new benchmark showing capable agents achieve near-perfect tool accuracy and minimal hallucination.