arxiv:2604.07023
Lei Wang
demolei
AI & ML interests
LLMs
Recent Activity
upvoted a paper about 4 hours ago
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It upvoted a paper about 4 hours ago
GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents upvoted a paper about 4 hours ago
The Verification Horizon: No Silver Bullet for Coding Agent RewardsOrganizations
arxiv:2603.28407
arxiv:2602.21015
arxiv:2602.09372
arxiv:2602.08237
arxiv:2602.01849
arxiv:2601.09688
arxiv:2506.04755
arxiv:2505.05315
arxiv:2504.11343
arxiv:2503.24235
arxiv:2410.04698
arxiv:2407.21018
arxiv:2310.16535
arxiv:2310.08395
arxiv:2305.04091
arxiv:2305.03453
arxiv:2304.01933
arxiv:2303.05063
arxiv:2211.01154
