The official datasets and models of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis"
XXHStudyHard
XXHStudyHard
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents upvoted a paper 2 months ago
Toward Generalist Autonomous Research via Hypothesis-Tree RefinementOrganizations
None yet
models 6
XXHStudyHard/EnvScaler-Qwen3-8B-SFT
308k • Updated • 5
XXHStudyHard/EnvScaler-Qwen3-4B-SFT
196k • Updated • 12
XXHStudyHard/EnvScaler-Qwen3-1.7B
2B • Updated • 10
XXHStudyHard/EnvScaler-Qwen3-8B
8B • Updated • 12
XXHStudyHard/EnvScaler-Qwen3-4B
4B • Updated • 15
XXHStudyHard/PLRD-IND-Pretraining
Updated • 1