LLM agents execute as long-lived, multi-stage workflows with substantial resource-demand variation across phases. Provisioning each agent or sandbox for its lifetime peak leads to low resource utilization, particularly for memory, whereas aggressive oversubscription risks memory contention, out-of-memory failures, and...
Yi-Fan Zhang, Xin-Kui Zhao, Rui-Xin Huang et al.· 0 citations
SOV-CAD is proposed, a framework that formulates CAD reconstruction as a sequential decision-making task and employs offline reinforcement learning with a Decision Transformer architecture that incorporates continuous visual feedback guided by geometric alignment rewards, resulting in a more accurate and human-like mod...
This work proposes CAPSUM, a capacity-aware admission policy with an elastic specialization, CAPSUM-E, and implements an exact local offline dynamic program and compares against direct common-model baselines and documented source-derived adapters for EDP-A, OREO, and uEDC-L.
Hailiang Zhao, Zi-Qi Wang, Yi-Fei Zhang et al.· 0 citations
Shiva-DiT, based on Residual-Based Differentiable Top-k Selection, provides four fidelity-latency operating points and reaches a 1.54x wall-clock speedup with competitive fidelity.
This work presents FAVA (Formal Authorization for Verified Agents), a permission-carrying authorization framework for agent execution that utilizes an LLM-guided Permission Intermediate Representation to translate ambiguous natural-language tasks into structured constraints.
Yifan Zhang, Xin-Kui Zhao, Sai-Da Liu et al.· arXiv.org· 3 citations
This work proposes ViSAGE, a multimodal agentic memory framework that constructs self-correcting, entity-centric memories and applies bidirectional memory refinement to propagate delayed identity evidence, retroactively unifying historical records and improving future reasoning.