arxiv:2609.32423
Yaorui SHI
yrshi
AI & ML interests
None yet
Recent Activity
authored a paper about 4 hours ago
PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins authored a paper about 4 hours ago
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning authored a paper about 4 hours ago
Learning to Act under Noise: Enhancing Agent Robustness via Noisy EnvironmentsOrganizations
arxiv:2606.24428
arxiv:2605.27141
arxiv:2605.27209
arxiv:2605.16143
arxiv:2605.06130
arxiv:2603.12631
arxiv:2602.10560
arxiv:2602.07594
arxiv:2601.21468
arxiv:2601.16725
arxiv:2510.10248
arxiv:2509.23040
arxiv:2505.11277
arxiv:2503.09427
arxiv:2502.12638
arxiv:2412.07819
arxiv:2408.15545
arxiv:2405.14225
