Curriculum learning, which organizes training samples according to their learning priority, has been widely adopted in reinforcement learning to improve training efficiency. However, existing methods commonly construct curriculum units using predefined data properties and estimate their utility by simply aggregating a...
Liang-Sheng Xu, Shu-Fan Shen, Zhong-Ni Hou et al.· 1 citation
This paper proposes Teacher-Evolution Self-Distillation (TESD), which enables the self-teacher to generate rollouts and receive environmental feedback based on task correctness and context independence and performs teacher-oriented optimization to continuously enhance the model's self-teaching capability during distill...
Shu-Fan Shen, Zhong-Ni Hou, Chao Bi et al.· 0 citations
LOOP is proposed, a Layer-level Recovery-Oriented On-Policy Pruning framework that interleaves pruning and recovery across multiple shots, and consistently outperforms one-shot baselines in average accuracy across different model scales and pruning ratios.
Liang-Sheng Xu, Shu-Fan Shen, Zhong-Ni Hou et al.· 0 citations
Agent memory architectures define how LLM agents store and reuse experience across tasks, but they are typically fixed after deployment, limiting their adaptability across task types. Recent self-evolving approaches instead adapt these memory architectures using execution feedback, typically represented as evaluation s...
Miao Su, Yu-Can Guo, Zi-Xuan Li et al.· 1 citation
R$^{2}$Adapter is a lightweight plug-in Routing and Rewriting Adapter designed to allocate queries between vanilla and graph-based RAG dynamically, providing an efficient and adaptive solution for hybrid RAG systems.
Yu-Can Guo, Miao Su, Saiping Guan et al.· 0 citations
Temporal Semantic Memory is proposed, a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory and incorporates the query's temporal intent on the semantic timeline.
Miao Su, Yu-Can Guo, Zhong-Ni Hou et al.· Annual Meeting of the Associ...· 12 citations
This work proposes ATLAS, a dual-horizon diagnostic evaluation framework for industrial tool-use agents that instantiates LLM judge interfaces as executable signals with explicit evidence scopes and decision boundaries, and evaluates ATLAS on Meituan Xiaotuan production traffic.
Wei Chen, Pei-Lun Zhou, Zhao-Yu Hu et al.· 0 citations
HiDiffTIR is proposed, a Hierarchical Difficulty-aware policy optimization framework for multi-turn TIR that consistently improves multi-turn TIR performance and tool invocation accuracy over strong RL baselines, highlighting the necessity of difficulty-aware credit assignment for effective policy optimization in tool-...
Yu-Can Guo, Xiao-Han Wang, Miao Su 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.