4 papers
ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation
Shengjie Jin, Hengbo Xu, Zelong Sun +2
Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI). Yet our experiments with existing meth…
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
Linfeng Fan, Yuan Tian, Ziwei Li +1
LLM agents increasingly rely on reusable skill libraries, but these skills silently decay as the external services, packages, APIs, and configurations they reference evolve. Existi…
From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models
Chenyue Zhou, Mingxuan Wang, Yanbiao Ma +19
Multimodal Large Language Models (MLLMs) strive to achieve a profound, human-like understanding of and interaction with the physical world, but often exhibit a shallow and incohere…
Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency
Yanbiao Ma, Wei Dai, Bowei Liu +5
Despite the fast progress of deep learning, one standing challenge is the gap of the observed training samples and the underlying true distribution. There are multiple reasons for…