Long-horizon LLM agents interact with their environments through complete assistant turns while generating each action token by token. We observe that critic values vary primarily across turns, motivating optimization anchored at turns with finer credit allocation among tokens. We propose Multiscale Policy Optimization...
Scaling supervised fine-tuning for working agents requires not only broad coverage of professional tasks, but also expert demonstrations that faithfully carry out professional workflows to completion. However, missing or inconsistent task information can disrupt expert demonstrations, weakening the resulting supervisio...
Ziyang Zeng, Ting-Yang Chen, Jia Deng et al.· 0 citations
Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce novelty assessments documented in Office Actions (OAs) across heterogeneous scientific and technical domains. However, existing benchmarks largely fo...
Qi-Yao Wang, Xin-Yi Chen, Hong-Bo Wang et al.· 0 citations
To serve as real-world personal assistants, streaming video models need persistent memory that retains past experiences for later use. Yet existing streaming benchmarks and methods often focus on individual continuous videos or short clips, overlooking that real-world interactions are often intermittent and require mem...
Jian-Guo Huang, Jin-Ming Liu, Qi-Yao Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.