Submit repository
Discover trends that matter
Daily explore
Live mentions
Topics
GitHub trending
Repositories
Developers
Repository engagements
Insights
Stats
ZJU-REAL/SDAR — GitHub trending stats & insights | Trendshift
Featured
Openhuman
ZJU-REAL/SDAR
#
AI agent
Official code for "Self-Distilled Agentic Reinforcement Learning"
Visit GitHub
Data last synced with GitHub 4 days ago
Python
88
6
189 contributors
last commit 4 days ago
last user commit 4 days ago
Apache License 2.0
website
created 5 days ago
Social mentions
Recent discussions about this repository across the web
智能体在训练时自己挑出做得好的轨迹当示范教材,自己教自己,不用人标注就能把复杂任务的成功率拉上去。 SDAR 是浙大 REAL 实验室提出的智能体强化学习方法。训练过程中自动筛选高分轨迹作为自产示范,再对策略做自我蒸馏,在 ALFWorld、WebShop 和 Search-QA 三个基准上全部超过标准 RL 基线。
@QingQ77 · x.com · 2 days ago
Self-Distilled Agentic Reinforcement Learning (SDAR) SDAR stabilizes multi-turn LLM agent training by gating self-distillation signals within GRPO, yielding +9.4% gains on ALFWorld and significant…
@HuggingPapers · x.com · 4 days ago
No trending activity
This repository has not yet been featured on GitHub Trending
Repository activities
repository's daily and monthly activities across stars, forks, merged PRs, issues, and closed issues