Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
NeoHorse Team, Guoliang Cao, Guohao Dai +34 authors
NeoHorse-1 uses agentic post-training with intelligent routing, structured feedback loops, and curriculum-based distillation to improve model capabilities across agent benchmarks.
Tong Zheng, Xidong Wu, Zheng Zhang +14 authors
Dream-RSI enables scalable recursive self-improvement by using historical discovery replay to evaluate exploration policies offline, reducing costly online evaluations.
Siwei Wu, Jincheng Ren, Yizhi Li +11 authors
ModularRSI improves agent harnesses through benchmark-independent, contrastive, modular evolution that isolates recurring deficiencies and evolves functional components independently.
Fang Wu, Da Xing, Yanjie Huang +16 authors
UniEvo-VL enables multimodal models to self-improve during inference by using internal critiques to guide diffusion-based generation without external teachers.
Peng Xia, Rujun Han, Zifeng Wang +11 authors
Regularized recursive self-improvement of agent harnesses improves out-of-distribution performance by constraining edit proposals and selections to favor reusable mechanisms over benchmark-specific memorization.
Junlin Yang, Che Jiang, Yu Fu +21 authors
OpenMLE enables recursive self-improvement in machine learning engineering via a full-stack system combining execution-grounded operator learning and long-horizon evolutionary search, significantly boosting benchmark performance with a 35B model.
Mind Lab, Vin Bo, Asher Cai +73 authors
Macaron-V1 is an open agent-model family that uses a Mixture-of-LoRA architecture and recursive self-improvement to enable continual learning and collaboration across specialized tasks.
Haozhe Liu, Tian Ye, Sensen Gao +11 authors
SoL-Pi improves token efficiency in autonomous coding agents through recursive self-improvement mechanisms, reducing costs by about one third while maintaining performance.
Wenyi Wu, Minghao Fu, Jieyu You +10 authors
RSIGame is an autonomous framework that uses recursive local and global self-improvement loops to iteratively refine generated games, internalize development experience into generators, and achieve higher quality with reduced token usage.
Haozhe Wang, Weijia Feng, Jinpeng Yu +8 authors
Researchers introduce benchmarks and a co-training framework to enable search-augmented visual generation that addresses open-ended world-knowledge gaps.
Sibo Zhu, Shicheng Fan, Xinyue Wang +3 authors
RSIAgent is a training-free multi-agent framework that enables recursive self-improvement via autonomous memory construction and broad-then-deep exploration to adapt digital agents to new environments.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号