Zilong Wang
12 papers · 535 citations
Most-cited papers
- Debug Like A Human: A Large Language Model Debugger Via Verifying Runtime Execution Step-by-step2024 · 157 citations
- Can Chatgpt Replace Stackoverflow? A Study On Robustness And Reliability Of Large Language Model Code Generation2023 · 144 citations
- Large Language Model Based Long-tail Query Rewriting In Taobao Search2023 · 99 citations
- LMDX: Language Model-based Document Information Extraction And Localization2023 · 61 citations
- Metaie: Distilling A Meta Model From LLM For All Kinds Of Information Extraction Tasks2024 · 26 citations
- Cocoabench: Evaluating Unified Digital Agents In The Wild2026
- Terminal-bench: Benchmarking Agents On Hard, Realistic Tasks In Command Line Interfaces2026
- Cograg+: Cognitive-level Guided Diagnosis And Remediation Of Memory And Reasoning Deficiencies In Professional Exam QA2026
- Agent Lightning: Train ANY AI Agents With Reinforcement Learning2025
Topics