Skills provide LLM agents with reusable procedural knowledge, making appropriate skill selection essential for reliable agent behavior. As skill libraries expand, distinguishing semantically similar candidates becomes increasingly difficult. Existing methods encode or rewrite skill descriptions for relevance-based rank...
Wen Xiao, Zi-Wei Zhang, Xingcheng Fu et al.· 0 citations
This workshop explores how graph learning can support emerging challenges in knowledge reasoning, temporal and multi-hop inference, and AI systems and investigates how advances in representation learning, structure-aware generalization, and efficient graph processing can contribute to trustworthy and scalable AI system...
Qing-Yun Sun, Zi-Wei Zhang, Xing-Cheng Fu et al.· Proceedings of the 32nd ACM...· 0 citations
It is shown that broader retrieval benefits visual DLM-RAG through selective evidence admission rather than unconditional evidence expansion, and the Entropy-Based Candidate Filter (ECF), a training-free evidence-admission framework is proposed, shows that broader retrieval benefits visual DLM-RAG through selective evi...
Jiankun Wang, Yi-Sen Gao, Zi-Wei Zhang et al.· 0 citations
This work proposes HiGram, an evolving hierarchical graph memory framework with path-level localization and rewriting, which organizes the memory into coarse-to-fine architecture composed of upper-level nodes and MemoryUnits, thereby reducing the amount of irrelevant information during retrieval.
Xiawei Yue, Boran Wang, Xiaoqing Zhang et al.· 0 citations
GTAlign is proposed, a surprisingly simple yet effective Graph-to-Table Alignment framework for text-free Graph Foundation Model, and a community-guided continual pre-training, where pseudo-labels derived from graph community are used to construct few-shot prediction episodes.
Chunyu Hu, Tianyin Liao, Ge Lan et al.· arXiv.org· 0 citations
DualG-MRAG is proposed, a Dual-tier framework that introduces a decoupled architecture comprising Macro-reasoning and Micro-matching Graphs for Multimodal RAG to suppress retrieval noise by isolating global structural reasoning from fine-grained evidence matching, and introduces a dynamic programming decoding mechanism...
This work introduces Evolutionary Rule Abstraction to distill generalized logic from optimization trajectories, overcoming the opacity of traditional evolution, and designs a Counterfactual Validation Module to strictly verify the causal reliability of abstracted rules.
Zhongyu Xing, Hanwen Luo, Maozu Guo et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
