Tag
This paper audits extractive prompt compressors across ten languages, revealing that English-trained models exhibit significant performance gaps on non-English text at high compression rates and proposes a translate-then-compress pipeline as a more effective alternative.
AGORA introduces an inference-free step-level prompt compressor for LLM agents that avoids the 'action-grammar destruction' failure mode of token-level compressors. It retains ≥75% uncompressed performance in 8 of 9 environments across backbones, using a structural parser, an always-keep floor, and a learned relevance scorer.