3 papers
cs.CY2026
InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems
Shaojie Shi, Zhengyu Shi, Lingran Zheng +15
Causal inference in social science relies on end-to-end, intervention-centered research-design reasoning grounded in real-world policy interventions, but current benchmarks fail to…
cs.AI2026
PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents
Yuxuan Fu, Xiaoyu Tan, Teqi Hao +2
Proactive agents must decide not only what to say but also whether and when to intervene. Many current systems rely on brittle heuristics or indiscriminate long reasoning, which of…
cs.CL2025
Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models
Teqi Hao, Xioayu Tan, Shaojie Shi +2
The personalization of black-box large language models (LLMs) is a critical yet challenging task. Existing approaches predominantly rely on context injection, where user history is…