Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?
Paper • 2609.27891 • Published • 12
Heng Lian
Pixelieee
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It? upvoted a paper 21 days ago
Repo0: Design-Driven Zero-to-All Code Generation upvoted a paper 21 days ago
ParaTempo: Efficient Parallel Reasoning via Temporal ConfidenceOrganizations
upvoted a paper about 7 hours ago
upvoted 3
papers 21 days ago
upvoted 5
papers about 1 month ago
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Paper • 2608.09802 • Published • 84
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
Paper • 2608.13667 • Published • 17
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Paper • 2608.18933 • Published • 13
Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution
Paper • 2607.11111 • Published • 16
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
Paper • 2607.18213 • Published • 47
upvoted 3
papers 3 months ago
upvoted a paper 4 months ago
upvoted 3
papers 8 months ago
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
Paper • 2602.07026 • Published • 141
Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
Paper • 2602.05386 • Published • 52
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
Paper • 2601.20833 • Published • 135
reacted to YerbaPage's post with 🤗🔥 8 months ago
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.
📚 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.
upvoted 2
papers 8 months ago