Skill^{infty}: Recursive Self-Improvement for Agent Skill Optimization
Paper • 2610.35434 • Published • 9
Trolle Karlsson
trollek
AI & ML interests
Stable Diffusion and small language models, but I'm a curious fella.
Recent Activity
upvoted a paper 2 days ago
Skill^{infty}: Recursive Self-Improvement for Agent Skill OptimizationOrganizations
None yet
upvoted 10
papers 2 days ago
Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization
Paper • 2610.31309 • Published • 18
Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges
Paper • 2610.35193 • Published • 24
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
Paper • 2610.33024 • Published • 28
Representation Redistribution in Sparse Autoencoders
Paper • 2610.21240 • Published • 57
Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions
Paper • 2610.37624 • Published • 8
Harness-Model Collaboration for Long-Horizon Continual Learning
Paper • 2610.34724 • Published • 22
Timestral
Paper • 2610.37585 • Published • 13
RSI Arena: Towards Recursive Self-Improvement with Human Feedback
Paper • 2610.33624 • Published • 38
Memory Tax: Dissecting the Net Value of Agent Memory
Paper • 2610.34073 • Published • 93
upvoted 7
papers 10 days ago
UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
Paper • 2610.10164 • Published • 9
Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads
Paper • 2610.05034 • Published • 11
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
Paper • 2610.09832 • Published • 17
Recurrent Looped Transformer
Paper • 2610.07591 • Published • 26
SanSi: A Looped Typed Decision Model for System 1.5 Thinking
Paper • 2610.07730 • Published • 21
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
Paper • 2610.11794 • Published • 44
Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression
Paper • 2610.09788 • Published • 18
upvoted 3
papers 11 days ago
Hybrid Reasoning Agents
Paper • 2610.18861 • Published • 42
LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation
Paper • 2610.19975 • Published • 78
Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine
Paper • 2610.22192 • Published • 41