4 papers
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
Jian Xie, Tianhe Lin, Zilu Wang +16
Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information.…
LASER: An Efficient Target-Aware Segmented Attention Framework for End-to-End Long Sequence Modeling
Tianhe Lin, Ziwei Xiong, Baoyuan Ou +8
Modeling ultra-long user behavior sequences is pivotal for capturing evolving and lifelong interests in modern recommendation systems. However, deploying such models in real-time i…
Implicit Reasoning in Transformers is Reasoning through Shortcuts
Tianhe Lin, Jian Xie, Siyu Yuan +1
Test-time compute is emerging as a new paradigm for enhancing language models' complex multi-step reasoning capabilities, as demonstrated by the success of OpenAI's o1 and o3, as w…
Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
Xinfeng Yuan, Siyu Yuan, Yuhan Cui +5
Large language models (LLMs) have demonstrated impressive performance and spurred numerous AI applications, in which role-playing agents (RPAs) are particularly popular, especially…