Training and evaluating interactive language agents typically requires rich user interactions, yet collecting human feedback is expensive and difficult to scale. Simulated users offer a scalable alternative, but they must both resemble real user behavior and provide useful learning experiences for agents. In contrast,...
Hoang Phan, Dat Huynh, A. Zhmoginov et al.· 0 citations
An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving single-shot accuracy at the cost of solution coverage. Although this trade-off has been observed in math and coding tasks, it need not extend to...
This paper proposes Hide-and-Seek, a framework that formulates VLA failure detection as a coarsely supervised learning problem that achieves state-of-the-art multi-task failure detection performance with a practical accuracy--timeliness trade-off under conformal prediction, and generalizes well to both seen and unseen...
S. Park, Wendi Li, Changdae Oh et al.· arXiv.org· 8 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.