Training agents for front-end web development requires demonstrations of code editing, execution, browser inspection and revision, yet public trajectories and reusable task environments remain limited. We introduce WebUniverse, a pipeline that constructs verifiable tasks with verified development trajectories from open...
Yao-Rui Ding, Feng-Qing Jiang, Yichen Feng et al.· 0 citations
A rule-to-image synthesis pipeline that extracts and expands puzzle rules from seed questions and generates executable rendering programs for puzzle assembly to tackle the challenge of image synthesis with grounded answers is proposed.
Can AI agents autonomously train useful language models and improve them using feedback from users? We introduce RSI Arena, a two-stage study of autonomous post-training as a step toward recursive self-improvement. Ten frontier models act as training agents, each starting from NVIDIA Nemotron 3.5 Lightning 30B-A3B Base...
Yue Huang, Yan-Bo Wang, Li-Chi Li et al.· 1 citation
SecProbe is introduced, a framework for adaptive evaluation that combines Item Response Theory (IRT) with on-demand synthesis of repository-scale vulnerability-repair tasks and achieves comparable agent ability estimates while requiring agents to solve up to 29.5\% fewer tasks.
Xiao-Nan Luo, Yue Huang, Ke-Han Guo et al.· 0 citations
How often models reward-hack without instructions to do so, how effective and detectable their methods are when hacking is allowed, and how they adapt when an LLM review panel returns its decision and reasons are studied.
Yue Huang, Zhangchen Xu, Yu-Chen Ma et al.· 1 citation
Safety-aware Contrastive Decoding (SafeCoDe) is introduced, a lightweight and model-agnostic decoding framework that dynamically adjusts token generation based on multimodal context that consistently improves context-sensitive refusal behaviors while preserving model helpfulness.