Heng Lian

Pixelieee's activity

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

liked a dataset 5 days ago

CrossSWE/CrossSWE-Bench

Viewer • Updated 8 days ago • 171 • 1.17k • 13

upvoted a paper 5 days ago

CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents

Paper • 2611.01484 • Published 7 days ago • 26

upvoted a paper 16 days ago

Deep Search in Real-World Web Environments

Paper • 2610.30181 • Published 20 days ago • 108

upvoted a paper 23 days ago

SWE-at-Scale: Scalable Issue Synthesis from Historical Bug Fixes

Paper • 2610.21359 • Published 24 days ago • 20

liked a model 23 days ago

SWE-at-Scale/swe-at-scale

Text Generation • Updated 24 days ago • 33 • 14

upvoted a paper about 2 months ago

Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?

Paper • 2609.27891 • Published Aug 21 • 19

upvoted 3 papers 2 months ago

Repo0: Design-Driven Zero-to-All Code Generation

Paper • 2608.19854 • Published Aug 20 • 17

ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

Paper • 2608.16425 • Published Aug 17 • 41

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

Paper • 2609.02783 • Published Sep 2 • 55

upvoted 5 papers 3 months ago

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Paper • 2608.09802 • Published Aug 10 • 74

Second Thought: Reasoning in Parallel as LLM Agents Act and Observe

Paper • 2608.13667 • Published Aug 13 • 18

SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution

Paper • 2608.18933 • Published Aug 19 • 14

Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution

Paper • 2607.11111 • Published Jul 13 • 13

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

Paper • 2607.18213 • Published Jul 20 • 46

upvoted a paper 4 months ago

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published Jun 26 • 83

upvoted 3 papers 5 months ago

FastContext: Training Efficient Repository Explorer for Coding Agents

Paper • 2606.14066 • Published Jun 12 • 79

LLM Agents Can See Code Repositories

Paper • 2606.14061 • Published Jun 12 • 21

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Paper • 2606.07297 • Published Jun 5 • 123

upvoted 2 papers 9 months ago

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Paper • 2602.07026 • Published Feb 2 • 140

Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening

Paper • 2602.05386 • Published Feb 5 • 51