Tracked topic
Papers arxiv:2604.26752 GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents Published on Apr 29 Submitted by Wenyi Hong on Apr 30 1 Paper of the day Z.ai Authors: , , , , , , , Yuanchang Yue , , , , , , , , Shuaiqi Duan , Sheng Yang , , , , , Abstract GLM-5V-Turbo integrates multim… …
… In this work, we analyze how LLMs process graph information through graph-token behavior in representative GLM architectures. Findings. We find that the internal saliency of graph tokens in GLMs is not equivalent to graph information utilization. …
… Claude reached 97.7%, while GLM-5.2 still failed 12%, GPT-5.6 Sol 18%, and Qwen3-235B 42%. …
… Experiments on Qwen3, Ministral, and GLM models reveal a persistent English--Chinese performance gap. …
… The use of GLM 5.2 is promising · Terminator 3, but yeah. Unhelpful. It is great strategy in defence. “ We ran the forensic analysis instead on GLM 5.2, an open-weight model, on our own infrastructure. …
… On this subset, frontier LLMs, including GPT-5.5, DeepSeek-V4-Pro, and GLM-5.1, reach only 30.00--45.67%, a substantial drop from BrowseComp, while Korean LLMs released through Korea's Proprietary AI Foundation Model program obtain only 0.00--10.33%. …
… We evaluate on WebShop, PinchBench, and Claw-Eval with Kimi-K2.5, GLM-5, and GPT-5.2. …
… The same planner also improves GPT-5.4 mini and GLM~5.1 from 45.0% and 58.5% to 60.0% and 71.0%. …
… On the full benchmark , OpenClaw with a minimal direct-diff adapter scores only 19.1% Pass@1 , whereas the full adapter reaches 73.4% with the same GLM 5.1 backbone, showing that adapter design is essential for enabling OpenClaw -style harness es to perform coding tasks effectively. …
… The flagship Macaron-V1-Venti combines a 744B GLM-5.2 base with four LoRAs for chat, agent, coding, and GenUI ; the Qwen3.6-based Macaron-V1-Tall 50B uses the same design for local deployment. …