Chmielewski

Eryk-Chmielewski's activity

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

upvoted 5 papers 1 day ago

Sliding-window beats linear attention

Paper • 2608.28444 • Published 5 days ago • 14

Fast Weight Attention for Continual Learning

Paper • 2608.27763 • Published 6 days ago • 26

Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO

Paper • 2608.27351 • Published 6 days ago • 19

StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments

Paper • 2608.24804 • Published 8 days ago • 35

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Paper • 2608.27549 • Published 6 days ago • 45

upvoted 3 papers 4 days ago

Code World Model: Coding Agent as World Brain

Paper • 2608.25927 • Published 7 days ago • 34

VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction

Paper • 2608.26005 • Published 7 days ago • 173

PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents

Paper • 2608.26530 • Published 6 days ago • 30

upvoted 12 papers 6 days ago

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Paper • 2608.17253 • Published 14 days ago • 95

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published 16 days ago • 105

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Paper • 2608.17310 • Published 15 days ago • 106

Agent Lightning v1.0: Towards Harnessed Agentic RL

Paper • 2608.17528 • Published 15 days ago • 32

ASI-Bench: At the Dawn of Artificial Superintelligence

Paper • 2608.17271 • Published 15 days ago • 62

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published 19 days ago • 169

Human-Centric Intelligence in the Era of Foundation Models: A Survey

Paper • 2608.18184 • Published 15 days ago • 9

AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale

Paper • 2608.20634 • Published 12 days ago • 12

FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills

Paper • 2607.21596 • Published 13 days ago • 21

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

Paper • 2608.20202 • Published 13 days ago • 34

Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

Paper • 2608.21156 • Published 12 days ago • 63

From Generation to Simulation: How Far Are World Models from Being True Simulators?

Paper • 2608.23070 • Published 9 days ago • 4