[2601.22571] PerfGuard: A Performance-Aware Agent for Visual Content Generation

Computer Science > Artificial Intelligence arXiv:2601.22571 (cs) [Submitted on 30 Jan 2026 (v1), last revised 5 Mar 2026 (this version, v2)] Title:PerfGuard: A Performance-Aware Agent for Visual Content Generation Authors:Zhipeng Chen, Zhongrui Zhang, Chao Zhang, Yifan Xu, Lan Yang, Jun Liu, Ke Li, Yi-Zhe Song View a PDF of the paper titled PerfGuard: A Performance-Aware Agent for Visual Content Generation, by Zhipeng Chen and 7 other authors View PDF HTML (experimental) Abstract:The advancement of Large Language Model (LLM)-powered agents has enabled automated task processing through reasoning and tool invocation capabilities. However, existing frameworks often operate under the idealized assumption that tool executions are invariably successful, relying solely on textual descriptions that fail to distinguish precise performance boundaries and cannot adapt to iterative tool updates. This gap introduces uncertainty in planning and execution, particularly in domains like visual content generation (AIGC), where nuanced tool performance significantly impacts outcomes. To address this, we propose PerfGuard, a performance-aware agent framework for visual content generation that systematically models tool performance boundaries and integrates them into task planning and scheduling. Our framework introduces three core mechanisms: (1) Performance-Aware Selection Modeling (PASM), which replaces generic tool descriptions with a multi-dimensional scoring system based on fine-grained ...