Data and models for the paper: LLM-in-Sandbox Elicits General Agentic Intelligence. Feel free to open an issue if you have any questions or problems!
Daixuan Cheng
daixuancheng
AI & ML interests
I study LLMs, from Pre-Training to Agent.
Recent Activity
upvoted a paper 3 days ago
Online Experiential Learning for Language Models authored a paper 18 days ago
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? upvoted a paper 18 days ago
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?Organizations
None yet
models 137
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL
4B • Updated • 943 • 1
daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL
9B • Updated • 3
daixuancheng/Qwen3-VL-8B-Thinking_stage3_MixAllRL_and_dataMixRatio_and_easy2hard
9B • Updated
daixuancheng/Qwen3-VL-8B-Thinking_stage2_MixAllRL_and_dataMixRatio
9B • Updated
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step20
9B • Updated
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step36
9B • Updated
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step4
9B • Updated • 1
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step10
9B • Updated
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_actor
Text Generation • 8B • Updated
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-20_actor
Text Generation • 8B • Updated