Unverified50% confidenceBenchmarkExact time
The Qwen 4B-level GUI agent trained with RL in WebHarbor can generalize to unseen tasks and performs comparably to leading open-source GUI web agents on four benchmarks.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/3/2026
First Seen
Valid until: 11/17/2026
Sources
Related Entities
Related Claims
UnverifiedThe GLM-4 series introduced tool calling, a code interpreter, and multimodal capabilities, and Zhipu AI open-sourced partial version weights via Hugging Face.63% similarUnverifiedOllama, LM Studio, Open WebUI, Docker Model Runner, LocalAI, and TabbyAPI are wrapper-layer tools that do not change underlying capabilities and only provide convenience for invocation.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130357API
curl https://kongchang.com/api/v1/knowledge/claims/1130357MCP
get_claim(id=1130357)