A lightweight RL policy called ContextCurator curates context for frozen LLM agents by reducing noise and keeping reasoning anchors, raising success rates on WebArena (36.4% to 41.2%) and DeepSearch (53.9% to 57.1%) while cutting token use substantially, with a 7B model matching GPT-4o performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
A lightweight RL policy called ContextCurator curates context for frozen LLM agents by reducing noise and keeping reasoning anchors, raising success rates on WebArena (36.4% to 41.2%) and DeepSearch (53.9% to 57.1%) while cutting token use substantially, with a 7B model matching GPT-4o performance.