3 papers
cs.AI2026
You Live More Than Once: Towards Hierarchical Skill Meta-Evolving
Xujun Li, Kehan Zheng, Mingyuan Zhao +7
Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric lea…
cs.LG2026
Data-Efficient RLVR via Off-Policy Influence Guidance
Erle Zhu, Dazhi Jiang, Yuan Wang +8
Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large language models (LLMs). Current data…
cs.AI2025
MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science
Erle Zhu, Yadi Liu, Zhe Zhang +5
Pre-trained on extensive text and image corpora, current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks. However, their p…