5 papers
Measuring and Mitigating Solution Mode Collapse in RLVR
Liv G. d'Aliberti, Marwa Abdulhai, Sofiia Druchyna +2
A language model (LM) can usually answer the same question in more than one way, but reinforcement learning with verifiable rewards (RLVR) is indifferent to which correct answer a…
Temporally Extended Mixture-of-Experts Models
Zeyu Shen, Peter Henderson
Mixture-of-Experts models, now popular for scaling capacity at fixed inference speed, switch experts at nearly every token. Once a model outgrows available GPU memory, this churn c…
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…
AutoCode: LLMs as Problem Setters for Competitive Programming
Shang Zhou, Zihan Zheng, Kaiyuan Liu +18
Writing competitive programming problems is exacting. Authors must: set constraints, input distributions, and edge cases that rule out shortcuts; target specific algorithms (e.g.,…
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
Zihan Zheng, Zerui Cheng, Zeyu Shen +16
Recent reports claim that large language models (LLMs) now outperform elite humans in competitive programming. Drawing on knowledge from a group of medalists in international algor…