An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically e...
Peng Xia, Ru-Jun Han, Zifeng Wang et al.· 4 citations· ⚡1
Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse. In this paper, we investigate why performance deteriorates over successive rounds and how to sustain self-evolution. Our analysis identifies two recurring quality problems in self-genera...
Jin-Yuan Li, Chengsong Huang, Lang-Lin Huang et al.· 0 citations
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically e...
Peng Xia, Ru-Jun Han, Zifeng Wang et al.· 3 citations· ⚡1
VisPlay is introduced, a self-evolving RL framework that enables VLMs to autonomously improve their reasoning capabilities from massive unlabeled image data and establishes a scalable path toward self-evolving multimodal intelligence.
Yicheng He, Chengsong Huang, Zongxia Li et al.· 0 citations
Environment Harness is proposed, a programmable layer of plug-in components that wraps a static environment to reshape its behavior without modifying the underlying logic, enabling continuous, targeted co-evolution of the policy and its environment.
Chengsong Huang, Zifeng Wang, Ru-Jun Han et al.· 11 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
