MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper • 2603.17187 • Published • 103
Yinxu Pan
cppowboy
AI & ML interests
RL for LLM, Code&Math Reasoning, Function Calling, Code Interpreter, Vision-Language Pretraining
Recent Activity
upvoted a paper about 5 hours ago
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild upvoted a paper 1 day ago
Online Experiential Learning for Language ModelsOrganizations
upvoted a paper about 5 hours ago
upvoted 5
papers 1 day ago
Online Experiential Learning for Language Models
Paper • 2603.16856 • Published • 45
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
Paper • 2603.16448 • Published • 51
InCoder-32B: Code Foundation Model for Industrial Scenarios
Paper • 2603.16790 • Published • 287
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
Paper • 2603.15726 • Published • 164
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Paper • 2603.15401 • Published • 15
Are these images publicly available?
1
#2 opened 2 days ago
by cppowboy
liked a
dataset 4 days ago
upvoted a paper 4 days ago
liked a
dataset 5 days ago
liked a
dataset 7 days ago
upvoted 3
papers 8 days ago
In-Context Reinforcement Learning for Tool Use in Large Language Models
Paper • 2603.08068 • Published • 39
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
Paper • 2603.07392 • Published • 17
OpenClaw-RL: Train Any Agent Simply by Talking
Paper • 2603.10165 • Published • 131
Amazing , it works with open claw
2
#39 opened 22 days ago
by 
infinityai
Can not reproduce evaluation results on SWE-Verified
#63 opened 9 days ago
by cppowboy
liked 4
datasets 10 days ago