8 papers
Probing RLVR training instability through the lens of objective-level hacking
Yiming Dong, Kun Fu, Haoyu Li +5
Prolonged reinforcement learning with verifiable rewards (RLVR) has been shown to drive continuous improvements in the reasoning capabilities of large language models, but the trai…
AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
Yuzhu Cai, Zexi Liu, Xinyu Zhu +3
Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current p…
ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
Zexi Liu, Jingyi Chai, Xinyu Zhu +5
The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-ba…
Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
Xinyu Zhu, Yuzhu Cai, Zexi Liu +8
The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic cohere…
SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?
Jingyi Chai, Shuo Tang, Rui Ye +8
The rapid advancements of AI agents have ignited the long-held ambition of leveraging them to accelerate scientific discovery. Achieving this goal requires a deep understanding of…
ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
Zexi Liu, Yuzhu Cai, Xinyu Zhu +6
As AI capabilities advance toward and potentially beyond human-level performance, a natural transition emerges where AI-driven development becomes more efficient than human-centric…