Zilong Wang
- Papers
- 16
Cite
Notes
Only stored in your browser.
Authored papers
16Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
arXiv 2026
CocoaBench: Evaluating Unified Digital Agents in the Wild
arXiv 2026
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
arXiv 2026
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
arXiv 2025
Training Language Models to Generate Quality Code with Program Analysis Feedback
arXiv 2025
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
arXiv 2025
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
arXiv 2025
Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's Nest
arXiv 2025
A Tale of LLMs and Induced Small Proxies: Scalable Agents for Knowledge Mining
arXiv 2025
TableRAG: Million-Token Table Understanding with Language Models
arXiv 2024
Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
arXiv 2024
Answer is All You Need: Instruction-following Text Embedding via Answering the Question
arXiv 2024
ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images
arXiv 2024
Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation
arXiv 2023
EmojiLM: Modeling the New Emoji Language
arXiv 2023
Tutel: Adaptive Mixture-of-Experts at Scale
arXiv 2022
Affiliations
Frequent co-authors
10from 16 papers