Daixuan Cheng

daixuancheng's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 5 hours ago

daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL

4B • Updated about 5 hours ago • 5 • 1

updated 2 datasets about 5 hours ago

daixuancheng/llm-in-sandbox-bench

Viewer • Updated about 5 hours ago • 2.78k • 256 • 1

daixuancheng/llm-in-sandbox-rl

Viewer • Updated about 5 hours ago • 4.66k • 83 • 1

upvoted a paper 2 days ago

Agent Lightning v1.0: Towards Harnessed Agentic RL

Paper • 2608.17528 • Published 4 days ago • 28

authored a paper 4 days ago

ClawGym II: Exploring Black-Box RL on Agent Harness

Paper • 2608.16798 • Published 5 days ago • 39

upvoted a paper 4 days ago

ClawGym II: Exploring Black-Box RL on Agent Harness

Paper • 2608.16798 • Published 5 days ago • 39

upvoted a paper about 1 month ago

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

Paper • 2607.12395 • Published Jul 14 • 100

liked a dataset about 2 months ago

ByteDance-Seed/EdgeBench

Viewer • Updated 26 days ago • 51 • 4.65k • 83

updated 3 datasets 2 months ago

RUC-AIBOX/ClawGym-Bench

Viewer • Updated Jun 16 • 200 • 134 • 2

RUC-AIBOX/ClawGym-Trajectory

Preview • Updated Jul 9 • 227 • 4

RUC-AIBOX/ClawGym-Task

Preview • Updated Jun 16 • 131 • 6

upvoted a paper 2 months ago

DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch

Paper • 2606.10728 • Published Jun 9 • 36

liked 3 datasets 3 months ago

RUC-AIBOX/ClawGym-Bench

Viewer • Updated Jun 16 • 200 • 134 • 2

RUC-AIBOX/ClawGym-Trajectory

Preview • Updated Jul 9 • 227 • 4

RUC-AIBOX/ClawGym-Task

Preview • Updated Jun 16 • 131 • 6

authored 2 papers 4 months ago

From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

Paper • 2508.07534 • Published Aug 11, 2025 • 2

ClawGym: A Scalable Framework for Building Effective Claw Agents

Paper • 2604.26904 • Published Apr 29 • 54

commented a paper 4 months ago

ClawGym: A Scalable Framework for Building Effective Claw Agents

Paper • 2604.26904 • Published Apr 29 • 54 •

4

upvoted a paper 4 months ago

ClawGym: A Scalable Framework for Building Effective Claw Agents

Paper • 2604.26904 • Published Apr 29 • 54

updated a model 4 months ago

daixuancheng/4-26-debugAdv_docker_rbs8_temp0.7_model-30BA3B-Sft_step99

31B • Updated Apr 29 • 3