Zexi Li

发表论文 7 篇 · 总被引 103 次 · h-index 3

代表论文

• WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models (2024 · Neural Information Processing Systems · 被引 109)
• MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents (2026 · arXiv.org · 被引 17)
• R3L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification (2026 · arXiv.org · 被引 11)
• WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents (2026 · arXiv.org · 被引 1)
• Understanding Synergistic Interactions among Pathology Foundation Models via Adaptive Fusion (2026)
• IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning (2026 · arXiv.org)