New benchmark tests agents on human needs with a ticking clock, no in-domain demos
ccloy · x · 2026-10-19
ccloy introduces an agent benchmark grounded in human needs that provides no in-domain demonstrations and features a clock that keeps ticking, testing agents under ongoing time pressure. The project is led by @caizhongang, Zhonghua Wu and Qingyi Tao, with a technical report, project page and open-source code released.
- Focus: human-need-grounded evaluation rather than curated in-domain tasks
- Key twist: a persistent ticking clock adds real-time pressure
- Resources: technical report, project page, and code are public
More from Research
- 1.9 MB extracted (not trained) LoRA fixes vertical color stripes in MOSS-Image SFT — Nynxz · 2026-10-19
- Three ways to execute a AND b AND c: DataFusion filter PR explained — Abhishekcur · 2026-10-19
- Why safety reports can't prove safety: the adversarial logic flaw — davidmanheim · 2026-10-19
- ACT3D trains VLMs to actively explore 3D worlds with RL, hitting 53.2% accuracy — UCSanDiego · 2026-10-19
- OPMD: ShanghaiTech distills teacher intermediate computations beyond output supervision — ShanghaiTech · 2026-10-19
- LexFrame: interpreting LM residual streams in the model's own semantics — Jian Gu · 2026-10-19