3 papers
cs.AI2026
RobustSGPO: Search-Space Control for Agent Harness Evolution
Zibo Zhao, Jijun Shi, Mo Zhou +9
Semantic-gradient-based prompt optimization (SGPO) improves agent harnesses using execution feedback, but its local update rule leaves the choice of edit scope and operation unreso…
cs.CL2026
Probing the Structure and Dynamics of LLM Value Expression through Value Conflicts
Kaicheng Zhang, Jingyi Xiao, Renjun Hu +3
Ethical evaluation of Large Language Models (LLMs) often characterizes model values as static and monolithic. In contrast, we argue that LLM value expression is better understood a…
cs.AI2026
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Yifan Zhou, Qihao Yang, Yan Li +14
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benc…