Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound
Baixi Sun, Le Chen, Anjir Ahmed Chowdhury +10
Agent memory grows as agents read inputs, reason, and call tools. Longer histories increase inference cost and eventually exceed the context window. LLM-based summarization reduces…
cs.AI2026
Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection
Anjir Ahmed Chowdhury, Syed Zawad, Feng Yan
While synthetic data generation with large language models (LLMs) is widely used in post-training pipelines, existing approaches typically generate full outputs before applying qua…