Transition-Aware Credit Assignment (TACA) is proposed, which targets the transition from reasoning to tool use through supervision of both call initiation and generation, and raises mean accuracy over MT-GRPO on six reasoning benchmarks by 4.61 percentage points.
Xiang-Yu Lu, Zhan-Ke Zhou, Jia-Zhe Ning et al.· 0 citations
Agents pair reasoning models with harnesses that organize model calls, execute tools, load skill instructions, and retain history in memory. Understanding agent performance requires linking execution conditions to outcomes, behavior, and resource use. We introduce AlphaDiana, a measurement system with modular interface...
Zhan-Ke Zhou, Zong-Ze Li, Weikai Huang et al.· 3 citations
It is observed that OPD-trained models maintain superior avg@K performance across sampling budgets, while the advantage in pass@K gradually shifts to the pre-OPD base models as K increases, suggesting that OPD primarily improves sampling efficiency rather than consistently expanding the student's reasoning capability b...