CL-bench Life: Can Language Models Learn from Real-Life Context?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918474841849856 |
|---|---|
| author | Dou, Shihan Shen, Yujiong Huang, Chenhao Ye, Junjie Chen, Jiayi Wang, Junzhe He, Qianyu Liu, Shichun Lv, Changze Lin, Jiahang Zhang, Jiazheng Zhang, Ming Liu, Shaofan Ji, Tao Yin, Zhangyue Zhang, Cheng Xie, Huaibing Hu, Jianglu Deng, Jingcheng Li, Lincheng Hu, Minda Wang, Shaolei Zhao, Syrus Wang, Weichao Lei, Yan Liu, Yang Xiao, Yanling Liu, Yiting Xu, Zenan Guo, Zhen Zhao, Ziliang Zhou, Pluto Gui, Tao Zhang, Qi Huang, Xuanjing Jiang, Yu-Gang Wang, Di Yao, Shunyu |
| author_facet | Dou, Shihan Shen, Yujiong Huang, Chenhao Ye, Junjie Chen, Jiayi Wang, Junzhe He, Qianyu Liu, Shichun Lv, Changze Lin, Jiahang Zhang, Jiazheng Zhang, Ming Liu, Shaofan Ji, Tao Yin, Zhangyue Zhang, Cheng Xie, Huaibing Hu, Jianglu Deng, Jingcheng Li, Lincheng Hu, Minda Wang, Shaolei Zhao, Syrus Wang, Weichao Lei, Yan Liu, Yang Xiao, Yanling Liu, Yiting Xu, Zenan Guo, Zhen Zhao, Ziliang Zhou, Pluto Gui, Tao Zhang, Qi Huang, Xuanjing Jiang, Yu-Gang Wang, Di Yao, Shunyu |
| contents | Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27043 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CL-bench Life: Can Language Models Learn from Real-Life Context? Dou, Shihan Shen, Yujiong Huang, Chenhao Ye, Junjie Chen, Jiayi Wang, Junzhe He, Qianyu Liu, Shichun Lv, Changze Lin, Jiahang Zhang, Jiazheng Zhang, Ming Liu, Shaofan Ji, Tao Yin, Zhangyue Zhang, Cheng Xie, Huaibing Hu, Jianglu Deng, Jingcheng Li, Lincheng Hu, Minda Wang, Shaolei Zhao, Syrus Wang, Weichao Lei, Yan Liu, Yang Xiao, Yanling Liu, Yiting Xu, Zenan Guo, Zhen Zhao, Ziliang Zhou, Pluto Gui, Tao Zhang, Qi Huang, Xuanjing Jiang, Yu-Gang Wang, Di Yao, Shunyu Computation and Language Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life. |
| title | CL-bench Life: Can Language Models Learn from Real-Life Context? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.27043 |