Chmielewski

Eryk-Chmielewski's activity

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

upvoted 5 papers about 13 hours ago

MemoryWalker: Stop Training Agents on Contexts They Never Saw

Paper • 2609.00865 • Published Sep 1 • 1

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

Paper • 2610.11794 • Published 26 days ago • 45

Cortex: Consolidating Context into Parametric Memory

Paper • 2610.20399 • Published 20 days ago • 73

Agentic Memory Management Is the Next Frontier of Information Retrieval

Paper • 2610.32464 • Published 11 days ago • 1

Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought

Paper • 2610.30755 • Published 12 days ago • 33

upvoted a collection 1 day ago

LFM2.5-24B Harness adapters

Collection

A collection of models trained with RL on specific adapters for more efficient agentic development • 6 items • Updated about 19 hours ago • 22

upvoted 2 papers 3 days ago

WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training

Paper • 2610.37161 • Published 7 days ago • 65

Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training

Paper • 2610.40362 • Published 5 days ago • 13

upvoted a collection 5 days ago

Ling Med

Collection

2 items • Updated 6 days ago • 3

upvoted 4 papers 6 days ago

On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models

Paper • 2610.32770 • Published 11 days ago • 49

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

Paper • 2610.33956 • Published 9 days ago • 46

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 8 days ago • 117

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents

Paper • 2610.33568 • Published 10 days ago • 69

upvoted 2 collections 8 days ago

Spark-X2.6

Collection

SOTA On-Device LLMs. Advancing the Frontier of On-Device Agents for Real-World Tasks. • 14 items • Updated 1 day ago • 43

Sage-A1.5

Collection

7 items • Updated 12 days ago • 16

upvoted a paper 8 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published Sep 17 • 216

upvoted a paper 12 days ago

Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model

Paper • 2510.18855 • Published Oct 21, 2025 • 74

upvoted a collection 12 days ago

MoESQ

Collection

Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores. • 6 items • Updated 12 days ago • 5

upvoted 2 papers 13 days ago

RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents

Paper • 2609.23466 • Published Sep 22 • 1

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Paper • 2608.09888 • Published Aug 10 • 747