DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
Paper • 2607.25675 • Published • 67
ganruoli
wittenberg
AI & ML interests
large language model
Recent Activity
upvoted a paper 21 days ago
Sample-Efficient Learning from Agent Experience upvoted a paper 21 days ago
AREX: Towards a Recursively Self-Improving Agent for Deep ResearchOrganizations
None yet
upvoted a paper 15 days ago
upvoted 3
papers 21 days ago
Sample-Efficient Learning from Agent Experience
Paper • 2607.21051 • Published • 20
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Paper • 2607.21461 • Published • 154
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Paper • 2607.18754 • Published • 25
很棒的工作，请问每个任务需要的 skills 需要自己装吗，还是运行脚本的时候自动安装了。
1
#1 opened 5 months ago
by wittenberg
authored a
paper almost 2 years ago
模型下载到本地后应该怎么推理，可以分享一下推理代码嘛？
#1 opened over 2 years ago
by wittenberg
cli_demo.py 在哪里？
2
#1 opened over 2 years ago
by wittenberg
updated 3
models over 2 years ago
liked a
dataset over 2 years ago
updated a
model almost 3 years ago