Agent-Omit trains 8B LLM agents via cold-start fine-tuning and omit-aware RL to adaptively drop unnecessary context, matching frontier models while delivering the best efficiency-performance balance on five benchmarks.
2.Only when task is finished can you provide final answer
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
-
Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
Agent-Omit trains 8B LLM agents via cold-start fine-tuning and omit-aware RL to adaptively drop unnecessary context, matching frontier models while delivering the best efficiency-performance balance on five benchmarks.