Huazheng Wang

huazhengwang's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers about 6 hours ago

EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?

Paper • 2610.04184 • Published 10 days ago • 21

AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering

Paper • 2609.32662 • Published 30 days ago

Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?

Paper • 2607.09996 • Published Jul 10

upvoted a paper about 11 hours ago

EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?

Paper • 2610.04184 • Published 10 days ago • 21

authored a paper 3 months ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 96

upvoted 2 papers 3 months ago

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Paper • 2605.24202 • Published May 22 • 18

Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism

Paper • 2605.30852 • Published May 29 • 8

authored 7 papers 5 months ago

Sliding Window Attention Adaptation

Paper • 2512.10411 • Published Dec 11, 2025 • 21

Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback

Paper • 2602.02369 • Published Feb 2 • 1

Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio

Paper • 2603.25926 • Published Mar 26 • 6

EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

Paper • 2605.11136 • Published May 11 • 11

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning

Paper • 2605.14212 • Published May 14 • 19

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Paper • 2605.24202 • Published May 22 • 18

Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism

Paper • 2605.30852 • Published May 29 • 8

liked a model 5 months ago

Mercury7353/MetaAgent-X

Reinforcement Learning • 8B • Updated May 15 • 88 • 6

upvoted 2 papers 5 months ago

MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning

Paper • 2605.14212 • Published May 14 • 19

EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales

Paper • 2605.11136 • Published May 11 • 11

upvoted a paper 10 months ago

Sliding Window Attention Adaptation

Paper • 2512.10411 • Published Dec 11, 2025 • 21

authored 2 papers about 1 year ago

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Paper • 2403.04783 • Published Mar 2, 2024 • 2

A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement

Paper • 2410.13828 • Published Oct 17, 2024 • 4