Dr-CiK: A Testbed for Foresight-Driven Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916053154529280 |
|---|---|
| author | Tang, Yihong Williams, Andrew Robert Ashok, Arjun Zheng, Vincent Zhihao Sun, Lijun Drouin, Alexandre Laradji, Issam H. Marcotte, Étienne Zantedeschi, Valentina |
| author_facet | Tang, Yihong Williams, Andrew Robert Ashok, Arjun Zheng, Vincent Zhihao Sun, Lijun Drouin, Alexandre Laradji, Issam H. Marcotte, Étienne Zantedeschi, Valentina |
| contents | Time series forecasting in real-world settings often depends not only on historical observations, but also on external context that must be actively discovered from noisy, heterogeneous information sources. Yet existing context-aided forecasting benchmarks typically assume that the supporting context is already provided, leaving open whether agents can identify it on their own. Therefore, we introduce Dr-CiK, a benchmark for evaluating whether agents can retrieve forecasting-relevant supporting context from a document corpus, filter out distractors, distill the retrieved context into forecast-useful evidence, and generate forecasts supported by that evidence. Through context ablations and evaluations of state-of-the-art deep research and forecasting methods paired together, we show that high-quality context substantially improves forecasting performance in Dr-CiK. However, most existing DR agents recover only a small fraction of the ground-truth supporting evidence (usually <5%), are frequently misled by distractors (>80% distractor citations), and can cause forecasters to perform worse with retrieved context than without context. Our results motivate research on foresight-driven agents that search for the right context to predict the future. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27904 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dr-CiK: A Testbed for Foresight-Driven Agents Tang, Yihong Williams, Andrew Robert Ashok, Arjun Zheng, Vincent Zhihao Sun, Lijun Drouin, Alexandre Laradji, Issam H. Marcotte, Étienne Zantedeschi, Valentina Artificial Intelligence Machine Learning Time series forecasting in real-world settings often depends not only on historical observations, but also on external context that must be actively discovered from noisy, heterogeneous information sources. Yet existing context-aided forecasting benchmarks typically assume that the supporting context is already provided, leaving open whether agents can identify it on their own. Therefore, we introduce Dr-CiK, a benchmark for evaluating whether agents can retrieve forecasting-relevant supporting context from a document corpus, filter out distractors, distill the retrieved context into forecast-useful evidence, and generate forecasts supported by that evidence. Through context ablations and evaluations of state-of-the-art deep research and forecasting methods paired together, we show that high-quality context substantially improves forecasting performance in Dr-CiK. However, most existing DR agents recover only a small fraction of the ground-truth supporting evidence (usually <5%), are frequently misled by distractors (>80% distractor citations), and can cause forecasters to perform worse with retrieved context than without context. Our results motivate research on foresight-driven agents that search for the right context to predict the future. |
| title | Dr-CiK: A Testbed for Foresight-Driven Agents |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.27904 |