Heng Lian

Pixelieee's activity

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

upvoted 5 papers 3 days ago

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

Paper • 2608.09802 • Published 14 days ago • 133

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

Paper • 2608.13667 • Published 10 days ago • 16

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

Paper • 2608.18933 • Published 5 days ago • 11

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

Paper • 2607.11111 • Published Jul 13 • 25

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

Paper • 2607.18213 • Published Jul 20 • 80

upvoted a paper about 2 months ago

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published Jun 26 • 116

upvoted 2 papers 2 months ago

FastContext: Training Efficient Repository Explorer for Coding Agents

Paper • 2606.14066 • Published Jun 12 • 96

LLM Agents Can See Code Repositories

Paper • 2606.14061 • Published Jun 12 • 20

upvoted a paper 3 months ago

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Paper • 2606.07297 • Published Jun 5 • 123

upvoted a paper 6 months ago

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

Paper • 2602.07026 • Published Feb 2 • 141

upvoted 2 papers 7 months ago

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

Paper • 2602.05386 • Published Feb 5 • 69

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Paper • 2601.20833 • Published Jan 28 • 183

reacted to YerbaPage's post with 🤗🔥 7 months ago

view post

Post

2187

🔥 SWE-Pruner can save up to 40% of your Claude Code cost without sacrificing performance. Try it out!

📚 SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents (2601.16746)
💻 https://github.com/Ayanami1314/swe-pruner

Drawing inspiration from how human programmers “selectively skim” source code during development and debugging, SWE-Pruner performs task-aware adaptive pruning for long contexts.

See translation

• 

🔥

6

6

🤗

3

3

👀

2

2

+

Reply

upvoted 6 papers 7 months ago

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

Paper • 2601.16746 • Published Jan 23 • 94

Controlled Self-Evolution for Algorithmic Code Optimization

Paper • 2601.07348 • Published Jan 12 • 115

KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions

Paper • 2601.04745 • Published Jan 8 • 59

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

Paper • 2601.06789 • Published Jan 11 • 82

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Paper • 2601.06943 • Published Jan 11 • 214

GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts

Paper • 2601.05110 • Published Jan 8 • 29