Agent performance is increasingly determined by the executable control layer around the model. TTHE improves fixed large language models (LLMs) by editing their harnesses from unlabeled traces, while…
Agent teams can cut inference cost by adapting the control program to a bounded workflow, improve deployed behavior through trace-driven harness edits, and diagnose long runs with checkpoint-level grading.
The day’s robotics papers focus on making Vision-Language-Action (VLA) policies execute reliably under real deployment conditions.
VLA teams can make three concrete changes to current robot policy work: add geometry-conditioned action decoding for fine manipulation, run a local latent-prompt adaptation pass before rollout, and store replay memory…