5 papers
Experience-Sensitive Game Learning: A Behavioral Study of Humans and Language Agents
Yingying Guo, Zhuoxuan Ju, Ruibo Ming +2
Large language model agents are increasingly evaluated through games, but most benchmarks emphasize final outcomes rather than how players learn from repeated interaction. We study…
Knowledge-Centric Agents for Workflow Generation in ComfyUI
Zhendong Li, Lei Sun, Ruibo Ming +4
Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular compositions. Existing large languag…
Evaluating Parameter Efficient Methods for RLVR
Qingyu Yin, Yulun Wu, Zhennan Shen +6
We systematically evaluate Parameter-Efficient Fine-Tuning (PEFT) methods under the paradigm of Reinforcement Learning with Verifiable Rewards (RLVR). RLVR incentivizes language mo…
Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
Qingyu Yin, Chak Tou Leong, Linyi Yang +7
Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain…
Position: Agentic Systems Constitute a Key Component of Next-Generation Intelligent Image Processing
Jinjin Gu
This position paper argues that the image processing community should broaden its focus from purely model-centric development to include agentic system design as an essential compl…