Zhiheng Xi

Zhiheng Xi on Hugging Face Daily Papers: 12 papers, 6 in the top 3 of their day, 744 upvotes.

1. AI Can Learn Scientific Taste 397 upvotes, #1 of 2026-03-17
2. SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents 5 upvotes, #16 of 2026-02-16
3. ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development 63 upvotes, #1 of 2026-01-20
4. Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction 71 upvotes, #3 of 2025-12-05
5. Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training 84 upvotes, #1 of 2025-01-22
6. ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use 9 upvotes, #14 of 2025-01-07
7. Distill Visual Chart Reasoning Ability from LLMs to MLLMs 18 upvotes, #7 of 2024-10-25
8. AgentGym: Evolving Large Language Model-based Agents across Diverse Environments 13 upvotes, #8 of 2024-06-07
9. StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback 44 upvotes, #2 of 2024-02-05
10. MouSi: Poly-Visual-Expert Vision-Language Models 9 upvotes, #13 of 2024-01-31
11. Secrets of RLHF in Large Language Models Part II: Reward Modeling 26 upvotes, #6 of 2024-01-12
12. Secrets of RLHF in Large Language Models Part I: PPO 30 upvotes, #2 of 2023-07-12

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.