Andreas Stöffelbauer

andreasskyscanner's activity

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

upvoted a paper about 8 hours ago

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper • 2610.11765 • Published 8 days ago • 237

upvoted 2 papers 1 day ago

Vela: User Behavior as Supervision Sparks LLM Intelligence

Paper • 2610.14709 • Published 6 days ago • 69

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published 7 days ago • 88

upvoted a paper 3 days ago

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

Paper • 2610.11291 • Published 7 days ago • 23

upvoted a paper 8 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 15 days ago • 111

upvoted a paper 9 days ago

Finetuning with Sampling: SFT Learns Better Than You Think

Paper • 2610.02140 • Published 15 days ago • 3

upvoted a paper 17 days ago

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

Paper • 2609.31002 • Published 21 days ago • 4

upvoted a paper 21 days ago

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

Paper • 2609.27334 • Published 23 days ago • 57

upvoted a paper 22 days ago

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

Paper • 2609.26550 • Published 24 days ago • 42

upvoted 3 papers 23 days ago

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

Paper • 2609.20519 • Published 29 days ago • 140

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 25 days ago • 230

MintAct: A Unified Visual Agent for Digital Environments

Paper • 2609.22083 • Published 28 days ago • 35

upvoted 2 papers 27 days ago

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

Paper • 2609.17708 • Published about 1 month ago • 80

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

Paper • 2609.17488 • Published about 1 month ago • 865

upvoted 2 papers 29 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 376

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

Paper • 2609.13443 • Published Sep 11 • 14

upvoted 4 papers about 1 month ago

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published Sep 14 • 255

Miles v0.1: Production-Level Post-Training

Paper • 2609.08368 • Published Sep 8 • 62

One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation

Paper • 2608.25936 • Published Aug 26 • 16

Group Adaptive Clipping Policy Optimization

Paper • 2609.00444 • Published Aug 31 • 10