Huazheng Wang

Huazheng Wang on Hugging Face Daily Papers: 10 papers, 2 in the top 3 of their day, 269 upvotes.

1. From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement 104 upvotes, #1 of 2026-08-03
2. When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs 17 upvotes, #20 of 2026-06-02
3. Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism 10 upvotes, #30 of 2026-06-02
4. MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning 18 upvotes, #15 of 2026-05-18
5. EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales 11 upvotes, #29 of 2026-05-13
6. Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio 8 upvotes, #26 of 2026-03-31
7. Sliding Window Attention Adaptation 17 upvotes, #6 of 2025-12-15
8. A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence 72 upvotes, #2 of 2025-07-29
9. Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems 6 upvotes, #14 of 2025-05-07
10. A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement 3 upvotes, #18 of 2024-10-21

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.