LiveMACEBench is introduced, a process-aware benchmark that uses live financial markets as a naturally evolving testbed for persistent LLM agents, demonstrating that mechanism access, effective mechanism use, and downstream performance are not interchangeable measures of agent capability.
Jun Zhao, Lei-Ming Fu, Yan Wen et al.· 0 citations
Initial evidence is provided that pretrained world knowledge can support reusable realized-progress evaluation and provide useful supervision for long-horizon agents.
Jun Zhao, Ji-Xin Tang, Yang Shu et al.· 0 citations
Reinforcement learning for long-horizon agents typically relies on sparse outcome-based rewards. This leads to a severe cold-start problem, as early-stage policies often fail to solve sampled tasks, leaving little useful reward signal for learning. To mitigate this problem, we use on-policy distillation (OPD) to provid...
You-Ling Huang, Tian-Kuo Xu, Jia-Ji Liu 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.