Andreas Stöffelbauer

andreasskyscanner's activity

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

upvoted a paper 2 days ago

DecisionRank: On-Policy Distillation for Decision-Model Rerankers

Paper • 2610.42128 • Published 6 days ago • 16

upvoted 2 papers 16 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 20 days ago • 49

Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents

Paper • 2610.18784 • Published 22 days ago • 119

upvoted a paper 21 days ago

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper • 2610.11765 • Published 28 days ago • 113

upvoted 2 papers 22 days ago

Vela: User Behavior as Supervision Sparks LLM Intelligence

Paper • 2610.14709 • Published 26 days ago • 77

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published 27 days ago • 68

upvoted a paper 24 days ago

When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better

Paper • 2610.11291 • Published 28 days ago • 26

upvoted a paper 29 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published Oct 1 • 76

upvoted a paper 30 days ago

Finetuning with Sampling: SFT Learns Better Than You Think

Paper • 2610.02140 • Published Oct 1 • 3

upvoted 6 papers about 1 month ago

ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker

Paper • 2609.31002 • Published Sep 25 • 5

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Paper • 2609.27334 • Published Sep 23 • 41

JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

Paper • 2609.26550 • Published Sep 22 • 35

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published Sep 17 • 91

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published Sep 21 • 164

MintAct: A Unified Visual Agent for Digital Environments

Paper • 2609.22083 • Published Sep 18 • 16

upvoted 5 papers about 2 months ago

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Paper • 2609.17708 • Published Sep 15 • 47

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published Sep 15 • 269

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 49

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

Paper • 2609.13443 • Published Sep 11 • 15

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published Sep 14 • 143