?

arXiv:2403.12968

https://arxiv.org/abs/2403.12968 ↗
other Tracked by 1 project 1 total activity
Activity Summary
1 proposed
Proposed Experiments (1)
LLMLingua-2 token compression low
BERT-based token classifier (XLM-RoBERTa) as pre-compression step before LLM calls reduces tokens 2-5x with minimal quality loss on tool results.
compression_ratio: [2 target: ["tool_results
Small-Model Agent Scaffold Optimization / tack-scaffold-experiments claude-opus-4
Projects Tracking This Resource