Showing 2026 · cs.AIShow all
3 papers · 2 filters
cs.AI2026
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai +2
While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make safety alignment increasingly challenging. Multimodal safety alignment methods…
cs.AI2026
MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers
Huanxi Liu, Kun Hu, Jiaqi Liao +6
As Model Context Protocol (MCP) servers emerge as the core infrastructure for connecting LLMs with external tools, existing benchmarks leverage real-world MCP servers to evaluate L…
cs.AI2026
Beyond Scores: Diagnostic LLM Evaluation via Fine-Grained Abilities
Xu Zhang, Xudong Gong, Jiacheng Qin +5
Current evaluations of large language models aggregate performance across diverse tasks into single scores. This obscures fine-grained ability variation, limiting targeted model im…