03:03
2026-08-20
aiunderstanding.org
artificial-intelligence
Agentic ESOpt proposes lower-memory fine-tuning for long-horizon AI agents
A six-author arXiv paper submitted on August 18, 2026, proposes Agentic ESOpt, a full-parameter fine-tuning framework for long-horizon language-model agents that uses evolution strategies instead of bโฆ