#machine learning
Jun 2026
The Interplay of Harness Design and Post-Training in LLM Agents
It is shown that harness-aware post-training not only improves in-distribution performance but also enables agents to robustly adapt to OOD settings, highlighting the importance of harness-aware post-training under such shifts.
Kyungmin Kim, Youngbin Choi, Seoyeon Lee et al.
· arXiv.org · 7 citations