Trolle Karlsson

trollek's activity

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

upvoted a paper about 12 hours ago

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

Paper • 2609.11682 • Published 15 days ago • 46

upvoted 4 papers about 13 hours ago

Recursive self-improvement of AI research agents

Paper • 2609.26457 • Published 3 days ago • 9

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published 21 days ago • 114

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 11 days ago • 214

Expert-Space Exploration in MoE Reinforcement Learning

Paper • 2609.13058 • Published 14 days ago • 8

upvoted 4 papers about 14 hours ago

GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills

Paper • 2609.21749 • Published 7 days ago • 18

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

Paper • 2609.07821 • Published 17 days ago • 16

AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

Paper • 2609.08572 • Published 17 days ago • 107

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

Paper • 2609.05903 • Published 20 days ago • 65

upvoted 2 papers 25 days ago

Looped Language Models Improve Compositional Tool Calling

Paper • 2608.18171 • Published Aug 17 • 23

Meta^n: Recursive Self-Improvement through Emergent Depth

Paper • 2608.24735 • Published Aug 25 • 16

liked a model 26 days ago

Quazim0t0/Byrne-15M-Looped

Text Generation • Updated 4 days ago • 1

upvoted a paper 29 days ago

Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation

Paper • 2608.15062 • Published about 1 month ago • 12

upvoted 3 papers about 1 month ago

AI for Auto-Research: Roadmap & User Guide

Paper • 2605.18661 • Published May 18 • 71

Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs

Paper • 2602.10388 • Published Feb 11 • 87

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

Paper • 2602.05400 • Published Feb 5 • 355

upvoted 3 papers about 2 months ago

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

Paper • 2607.28617 • Published Jul 30 • 37

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Paper • 2604.04247 • Published Apr 5 • 30

SePO: Self-Evolving Prompt Agent for System Prompt Optimization

Paper • 2606.04465 • Published Jun 3 • 7

liked a model about 2 months ago

CoRal-project/roest-v3-chatterbox-500m

Text-to-Speech • Updated 23 days ago • 104 • 6