Chmielewski

Eryk-Chmielewski's activity

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

upvoted 7 papers 1 day ago

Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems

Paper • 2602.03695 • Published 4 days ago • 1

Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing

Paper • 2602.04837 • Published 3 days ago • 1

MARS: Modular Agent with Reflective Search for Automated AI Research

Paper • 2602.02660 • Published 5 days ago • 56

No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs

Paper • 2602.02103 • Published 5 days ago • 64

AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration

Paper • 2602.03786 • Published 4 days ago • 80

HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing

Paper • 2602.03560 • Published 4 days ago • 40

daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently

Paper • 2602.02619 • Published 5 days ago • 47

upvoted 3 papers 2 days ago

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

Paper • 2602.03411 • Published 4 days ago • 34

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Paper • 2602.03419 • Published 4 days ago • 38

SWE-Universe: Scale Real-World Verifiable Environments to Millions

Paper • 2602.02361 • Published 5 days ago • 56

upvoted 10 papers 3 days ago

From Atomic to Composite: Reinforcement Learning Enables Generalization in Complementary Reasoning

Paper • 2512.01970 • Published Dec 1, 2025 • 2

Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision

Paper • 2509.14234 • Published Sep 17, 2025 • 6

How AI Impacts Skill Formation

Paper • 2601.20245 • Published 10 days ago • 8

Behavior Knowledge Merge in Reinforced Agentic Models

Paper • 2601.13572 • Published 18 days ago • 24

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes

Paper • 2601.18795 • Published 12 days ago • 1

Expanding the Capabilities of Reinforcement Learning via Text Feedback

Paper • 2602.02482 • Published 5 days ago • 2

Toward Efficient Agents: Memory, Tool learning, and Planning

Paper • 2601.14192 • Published 18 days ago • 54

Closing the Loop: Universal Repository Representation with RPG-Encoder

Paper • 2602.02084 • Published 5 days ago • 81

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones

Paper • 2509.25123 • Published Sep 29, 2025 • 22

Q-learning with Adjoint Matching

Paper • 2601.14234 • Published 18 days ago • 1