By storing KV caches of prior reasoning traces and retrieving them during generation, LAG improves LLM agent accuracy and efficiency over standard agentic systems and reflection methods.
Thought-retriever: Don’t just retrieve raw data, retrieve thoughts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation
By storing KV caches of prior reasoning traces and retrieving them during generation, LAG improves LLM agent accuracy and efficiency over standard agentic systems and reflection methods.