7 papers
S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents
Yao Dong, Xinglin Xiao, Liwei Dong +5
Deep research agents aim to solve complex knowledge-intensive tasks through long-horizon planning, evidence gathering, reasoning, and report generation. While recent progress in se…
A Survey on the Applications of Generative Artificial Intelligence in Automated Driving Systems Test Scenario Generation Methods
Ji Zhou, Yongqi Zhao, Yixian Hu +4
Ensuring the safety and reliability of Automated Driving Systems (ADS) remains a critical challenge, as traditional verification methods such as large-scale on-road testing are pro…
SWE-IF: Aligning Code Evaluation with Human Preference
Ming Zhong, Xiang Zhou, Ting-Yun Chang +9
Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes the…
S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images
Qingxiao Li, Lifeng Xu, QingLi Wang +4
We present S1-VL, a multimodal reasoning model for scientific domains that natively supports two complementary reasoning paradigms: Scientific Reasoning, which relies on structured…
Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
Yexiang Liu, Zekun Li, Zhi Fang +3
Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting str…
LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems
Nan Xu, Xuezhe Ma
Interestingly, LLMs yet struggle with some basic tasks that humans find trivial to handle, e.g., counting the number of character r's in the word "strawberry". There are several po…