Joint reinforcement learning and self-distillation combines task rewards with dense teacher guidance for agent training, but their gradients can partly cancel. A mixing coefficient controls relative scale without selectively removing opposing components. We present CORD, a general framework for conflict-aware optimizat...
Wen-Hao Yu, Zheng-Cheng Wang, Jia-Hong Liu et al.· 0 citations
Across multi-hop QA and long-horizon web reasoning tasks, StepKV sustains accuracy under low KV budgets where token-level baselines degrade sharply, offering a more robust efficiency-accuracy trade-off for multi-step agent inference.
Bo-Yu Feng, Jia-Hong Liu, Yi-Fan Li et al.· 0 citations
It is argued that long-horizon personalization should instead model memory as a user-specific dynamical state space with locally heterogeneous geometry, which captures stable versus volatile regions, variable-rate drift, heterogeneous neighborhoods, and uncertainty about current user state.
Jia-Hong Liu, Wenhao Yu, Ze-Xuan Qiu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.