Qingyun Wang

eaglew's activity

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

authored 2 papers 5 days ago

Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization

Paper • 2610.01017 • Published 13 days ago • 8

It Takes Workflows to Evolve Better Workflows

Paper • 2610.01026 • Published 13 days ago • 10

upvoted 2 papers 5 days ago

Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization

Paper • 2610.01017 • Published 13 days ago • 8

It Takes Workflows to Evolve Better Workflows

Paper • 2610.01026 • Published 13 days ago • 10

upvoted 2 papers 7 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 13 days ago • 111

LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures

Paper • 2610.04292 • Published 11 days ago • 38

authored 2 papers about 2 months ago

Decoupled Physical Modeling and Execution for Physics Reasoning

Paper • 2608.22126 • Published Aug 22

Enhancing Software Engineering Through Closed-Loop Memory Optimization

Paper • 2606.05646 • Published Jun 4

authored a paper 2 months ago

Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning

Paper • 2608.04926 • Published Aug 5 • 9

upvoted 2 papers 2 months ago

CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning

Paper • 2608.02833 • Published Aug 3 • 5

Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning

Paper • 2608.04926 • Published Aug 5 • 9

authored a paper 2 months ago

CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning

Paper • 2608.02833 • Published Aug 3 • 5

authored a paper 5 months ago

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning

Paper • 2605.03314 • Published May 6 • 4

commented 2 papers 6 months ago

CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation

Paper • 2510.17853 • Published Oct 15, 2025 • 9 •

3

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

Paper • 2510.07731 • Published Oct 9, 2025 • 5 •

5

authored a paper 7 months ago

SciDER: Scientific Data-centric End-to-end Researcher

Paper • 2603.01421 • Published Mar 2 • 6

upvoted a paper 8 months ago

Anagent For Enhancing Scientific Table & Figure Analysis

Paper • 2602.10081 • Published Feb 10 • 2

authored a paper 8 months ago

Anagent For Enhancing Scientific Table & Figure Analysis

Paper • 2602.10081 • Published Feb 10 • 2

authored 2 papers 12 months ago

MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness

Paper • 2504.21773 • Published Apr 30, 2025 • 1

CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation

Paper • 2510.17853 • Published Oct 15, 2025 • 9