This paper introduces Agentic Test-Time Training (aTTT), a novel framework that continuously adapts model weights during multi-turn agent episodes to prevent performance degradation over long trajectories. By utilizing a token-level reweighting method to mitigate self-training drift on repeated states, it provides a highly foundational mechanism for sustaining agent reasoning and competence in long-horizon environments.
Short on time? Watch the video overview of this paper.
Listen on: Spotify · Apple Podcasts · Amazon Music · YouTube
Follow the show: YouTube · Medium · X · LinkedIn · Bluesky · Threads · Instagram · TikTok · Facebook · Telegram