الباحثون

Weixuan Xu

المنشورات 2

نسخة أولية وصول مفتوح

GenMem: Generative Symbolic Memory for Self-Evolving Harness

Xinke Jiang, Tao Feng, Weixuan Xu وآخرون · 2026

Long-term memory supports the self-evolution of LLM agents by retaining experience and skills across tasks and enabling their retrieval, reuse, and revision in subsequent long-horizon decision-making. Yet existing memory management approaches remain limited to discriminative retrieval and to address the sparse, hierarc …

نسخة أولية وصول مفتوح

When Sparse Reward Meets Dense Distillation: Training Dynamics of On-Policy Distillation

Xinke Jiang, Tao Feng, Zhibang Yang وآخرون · 2026

Reinforcement learning with verifiable rewards provides a sparse post-training signal: a single binary outcome evaluates the entire rollout, and every token receives the same sequence-level advantage regardless of its individual contribution. To complement this sparse supervision, a growing family of methods adds a sca …

المؤلفون المشاركون