Zhiwei Zhang

Jameszhiwei

3 1

AI & ML interests

None yet

Recent Activity

upvoted a paper about 2 months ago

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

upvoted a paper about 2 months ago

Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering

updated a model 4 months ago

Jameszhiwei/Qwen2-7B-ours-alfworld-gs50

View all activity

Organizations

None yet

upvoted 2 papers about 2 months ago

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Paper • 2605.30621 • Published May 28 • 23

Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering

Paper • 2605.05678 • Published May 7 • 6

upvoted a paper 9 months ago

Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph

Paper • 2511.00086 • Published Oct 29, 2025 • 42