TIME

Name: TIME
Author: sylvain-wei

sylvain-wei May 13, 2025

30 copies 0 downloads

[NeurIPS 2025 D&B (Spotlight🌟)] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario

Agent Definition

<div align="center">

# ⏳ TIME


<div align="center" style="margin: 20px 0;">


[![Paper](https://img.shields.io/badge/📄-Paper-red?style=for-the-badge)](https://arxiv.org/abs/2505.12891)
[![Code](https://img.shields.io/badge/💻-Code-black?style=for-the-badge&logo=github)](https://github.com/sylvain-wei/TIME)
[![TIME Dataset](https://img.shields.io/badge/🤗-TIME%20Dataset-yellow?style=for-the-badge)](https://huggingface.co/datasets/SylvainWei/TIME)
[![TIME-Lite](https://img.shields.io/badge/⚡-TIME--Lite-blue?style=for-the-badge)](https://huggingface.co/datasets/SylvainWei/TIME-Lite)
[![TIME-Lite](https://img.shields.io/badge/🌐-ProjectPage-green?style=for-the-badge)](https://sylvain-wei.github.io/TIME/)
[![TIME-Lite](https://img.shields.io/badge/📣-NeurIPS25-purple?style=for-the-badge)](https://neurips.cc/virtual/2025/poster/121417)


</div>




<h2>[NeurIPS'25 Spotlight] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios</h2>

<div align="center" style="margin: 20px 0;">
  <img src="assets/Peking_University_logo.svg" alt="Peking University" height="60" style="margin: 0 40px;"/>
  <span style="display: inline-block; width: 50px;"></span> <!-- 空白间距 -->
  <img src="assets/Noah_s_ark_lab_logo.png" alt="Huawei Noah's Ark Lab" height="45" style="margin: 0 40px;"/>
</div>

</div>

> 🎉🎉 **Congratulations!** This paper has been accepted as **<span style="color: #dc3545; font-weight: bold;">NeurIPS 2025 Spotlight 🌟🔥</span>** at D&B track.
> 
**🌟 If you found this work helpful, please consider giving us a ⭐ on GitHub!**

[![GitHub stars](https://img.shields.io/github/stars/sylvain-wei/TIME?style=social&label=Star)](https://github.com/sylvain-wei/TIME)
[![Hugging Face](https://img.shields.io/badge/🤗-Hugging%20Face-yellow)](https://huggingface.co/datasets/SylvainWei/TIME)

</div>


## 📋 Project Information

<!-- <img src="assets/logo.png" alt="TIME Logo" width="200"/> -->

> **Authors**: Shaohang Wei, Wei Li, Feifan Song, Wen Luo, Tianyi

Comments

More Agents

View all

hybrid-model-workflow

HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收，低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。

ph4ble

Dynamic-Review-Agent

An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.

1838177

StellarOS-Watch

基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架；集成生产级 OTA 回滚保护机制与高带宽（921600 baud）串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互，是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。

chenshuang888