Principled Thoughts for Latent Recursive LLM Systems
Paper • 2609.36159 • Published • 5
Trolle Karlsson
trollek
AI & ML interests
Stable Diffusion and small language models, but I'm a curious fella.
Recent Activity
upvoted a paper about 1 hour ago
Principled Thoughts for Latent Recursive LLM Systems upvoted a paper about 1 hour ago
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents upvoted a paper about 1 hour ago
Scheduling Recursive Reasoning in Looped TransformersOrganizations
None yet
upvoted 4
papers about 1 hour ago
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
Paper • 2609.37236 • Published • 38
Scheduling Recursive Reasoning in Looped Transformers
Paper • 2609.36653 • Published • 16
SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale
Paper • 2609.38822 • Published • 6
upvoted 10
papers about 3 hours ago
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Paper • 2609.01343 • Published • 92
Improving Test-Time Scaling with Adaptive Looped Transformers
Paper • 2609.35748 • Published • 57
WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models
Paper • 2609.23033 • Published • 8
FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates
Paper • 2609.29812 • Published • 3
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
Paper • 2608.09444 • Published • 13
LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers
Paper • 2609.17184 • Published • 2
Looped Transformers as Optimizers
Paper • 2609.37379 • Published • 1
Loop Dropout: Regularizing Shared Updates in Looped Language Models
Paper • 2609.34218 • Published • 1
T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning with Dynamic Routing
Paper • 2609.15160 • Published • 1
Decoding Looped Transformers Better for (Almost) Free
Paper • 2610.02185 • Published • 25
upvoted 6
papers 9 days ago
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
Paper • 2609.11682 • Published • 46
Recursive self-improvement of AI research agents
Paper • 2609.26457 • Published • 27
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Paper • 2609.05571 • Published • 119
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Paper • 2609.14857 • Published • 215
Expert-Space Exploration in MoE Reinforcement Learning
Paper • 2609.13058 • Published • 8
GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills
Paper • 2609.21749 • Published • 19