yang

dearaj23's activity

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

upvoted a paper 14 days ago

Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

Paper • 2609.26637 • Published 21 days ago • 27

upvoted 2 papers 22 days ago

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published 29 days ago • 410

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 29 days ago • 252

upvoted 3 papers 27 days ago

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

Paper • 2609.03241 • Published Sep 3 • 51

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Paper • 2609.04148 • Published Sep 3 • 211

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Paper • 2609.11977 • Published Sep 4 • 119

upvoted 2 papers about 1 month ago

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published Aug 31 • 274

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published Aug 31 • 98

authored a paper 6 months ago

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Paper • 2603.28342 • Published Mar 30 • 24

upvoted a paper 7 months ago

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Paper • 2603.28342 • Published Mar 30 • 24

updated 2 collections 9 months ago

Agent Benchmark

Collection

2 items • Updated Jan 19

multi-agent

Collection

4 items • Updated Jan 17

upvoted a paper 10 months ago

Memory in the Age of AI Agents

Paper • 2512.13564 • Published Dec 15, 2025 • 160

liked a dataset 11 months ago

openai/gsm8k

Benchmark • Updated Mar 23 • 17.6k • 1.01M • 1.98k

upvoted 2 papers 11 months ago

SRMT: Shared Memory for Multi-agent Lifelong Pathfinding

Paper • 2501.13200 • Published Jan 22, 2025 • 70

MIRIX: Multi-Agent Memory System for LLM-Based Agents

Paper • 2507.07957 • Published Jul 10, 2025 • 80

authored a paper 12 months ago

EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning

Paper • 2510.17928 • Published Oct 20, 2025 • 4

upvoted a paper 12 months ago

EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning

Paper • 2510.17928 • Published Oct 20, 2025 • 4

updated 2 collections 12 months ago

multi-agent

Collection

4 items • Updated Jan 17

RL

Collection

2 items • Updated Oct 20, 2025