A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Mingxuan Zheng, Yujin Zhou, Chuxue Cao, et al.
SkillProx introduces a proximal-gradient-inspired framework for self-evolving agent skills, combining closed-loop diagnostic evolution with utility-aware proximal refinement to improve accuracy by 3.0 points over gradient-based baselines.
Unknown
This paper introduces a sim-to-real approach using randomized-to-canonical adaptation networks to transfer a vision-based closed-loop grasping reinforcement learning agent from simulation to a real robot.
Unknown
Coevolve introduces a closed-loop framework where LLM agents and training data co-evolve, enabling agents to improve through mutual adaptation rather than static data.
Unknown
This paper presents the first data scaling law for generative world models in embodied settings, uncovering how data volume impacts simulation fidelity and downstream policy learning.
Zhiqiang Liu, Wenhui Dong, Yilan Tan, et al.
TOBench is a task-oriented omni-modal benchmark for evaluating real-world tool-using agents through closed-loop multimodal verification.