Entities · Models
GLM-5
9 articles tagged with this entity.
-
GLM-5 Serving Parameter Tuning for OpenClaw: Single-Deployment MaaS Inference Optimization for Long-Context Agent Workloads
-
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection
-
GLM-5.2 is probably the most powerful text-only open weights LLM
-
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
-
GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models
-
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
-
SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers
-
Toward Autonomous Long-Horizon Engineering for ML Research
-
Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations