6 papers
Aspire: Can Models Self-Evolve from Vague Goals?
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +18
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability…
StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows
Liya Zhu, Xin Ma, Tao Liu +35
Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on re…
Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents
Zining Huang, Haoran Que, Hong Zeng +8
When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference: they concentrate rules in t…
DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
Fangyu Lei, Jinxiang Meng, Yiming Huang +14
Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into de…
Virtual Width Networks
Seed, Baisheng Li, Banggu Wu +115
We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN d…
WideSearch: Benchmarking Agentic Broad Info-Seeking
Ryan Wong, Jiawei Wang, Junjie Zhao +10
From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid de…