3 papers
cs.CR2026
SkillBloat: Token Amplification Attacks via Skill Injection in LLM Coding Agents
Yuanjin Zheng, Jingbang Chen
Agent skills extend coding agents with task-specific instructions, scripts, and resources, but they also create a trusted instruction channel that can be abused beyond conventional…
cs.LG2025
FrontierCS: Evolving Challenges for Evolving Intelligence
Qiuyang Mang, Wenhao Chai, Zhifei Li +48
We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competiti…
cs.CL2025
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
Youliang Yuan, Qiuyang Mang, Jingbang Chen +7
In this paper, we observe that current models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability. This is evidenced by a high…