AI RESEARCH
AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents
arXiv CS.AI
•
ArXi:2605.26596v1 Announce Type: new The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (en, backbone, method) cells spanning two independent token-level method families, every cell collapses to mean reward <= 0.05 despite 1.3-13.3x realized compression.