LZX

LZX on Hugging Face Daily Papers: 9 papers, 5 in the top 3 of their day, 570 upvotes.

1. Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning 35 upvotes, #8 of 2026-07-22
2. Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable 216 upvotes, #1 of 2026-07-16
3. Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading 74 upvotes, #2 of 2026-07-13
4. Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills 21 upvotes, #17 of 2026-04-10
5. MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data 51 upvotes, #3 of 2026-03-11
6. First Frame Is the Place to Go for Video Content Customization 51 upvotes, #4 of 2025-11-21
7. VisPlay: Self-Evolving Vision-Language Models from Images 41 upvotes, #4 of 2025-11-20
8. R-Zero: Self-Evolving Reasoning LLM from Zero Data 107 upvotes, #2 of 2025-08-08
9. HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models 27 upvotes, #2 of 2023-10-24

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.