Story
arxiv_cs_ai · Nov 3, 2026 · paper
Source brief
Meta$^2$: Precomputing Reusable Knowledge for Online Harness Evolution in Long-Horizon Agents
arxiv.orgNov 3, 2026
original source linked
In brief
Harness optimization improves long-horizon agents by refining the prompts, tools, memory, and hooks around a frozen model. Offline methods can learn from completed trajectories, but deploy one shared harness that may...
Feed lens
agentharnesseval