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
Cognitive Differentiation in Skill Evolution (CDSE), which evolves a unified skill through four functionally distinct yet coordinated components: Meta, Experience, Tool, and Script, is proposed and achieves the highest scores in all 36 settings.
Ye-Wei Zhao, De-Rong Xu, Wei Chen et al.· 0 citations
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
This work proposes CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission, and shows conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence.
Layer-level pruning is attractive for large language model (LLM) deployment as it reduces the model size while preserving a dense architecture that can be efficiently executed on standard hardware. Current methods typically follow a one-shot paradigm, which first removes selected layers to reach a target model size and...
Liang-Sheng Xu, Shu-Fan Shen, Zhong-Ni Hou et al.· 0 citations
The proposed ToolEX (Tool Equivalent eXpansion), a framework that automatically discovers and annotates the tool combinations functionally equivalent to the labeled ones, and confirms that the one-to-one problem extends beyond tool retrieval.
Yan-Yu Zhu, Chen-Heng Zhang, Shao-Shen Chen et al.· 0 citations
This work introduces SAKI (Supervision Allocation with KL-constrained Interpolation), which combines a KL-constrained teacher-guided rollout with maximal coupling and reuses realized accept/correction events to route token-level supervision.
Miteto Wei, Xiao-Han Wang, Ze-Hao Chen et al.· 0 citations
Temperature-Grouped Reinforcement Learning (TGRL), which turns temperature-induced diversity into an explicit training signal, and reaches equivalent accuracy up to 36% faster than strong RLVR baselines without expanding the rollout budget.
Zi-Han Lin, Xiao-Han Wang, Jie Cao et al.· arXiv.org· 0 citations
Experiments in controlled multi-solution environments and continual post-training settings across multiple model scales demonstrate that CoKL achieves a more favorable balance between target-task improvement and prior-capability retention than existing regularization methods.
Li Wang, Xiao-Dong Lu, Xiao-Han Wang et al.· 0 citations
OSOL, which designates a focus domain at each iteration, uses the preceding checkpoint footprint to rank token-level rebound risk, and applies a drift-ranked, adaptively scaled correction within the standard GRPO update, is proposed, which suppresses the targeted cross-step output backtracking component.
Zi-Han Lin, Xiao-Han Wang, Jie Cao et al.· 1 citation
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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.