DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems
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_ | 1866909981357375488 |
|---|---|
| author | Röpke, Willem Coward, Samuel Lupu, Andrei Foster, Thomas Rocktäschel, Tim Foerster, Jakob |
| author_facet | Röpke, Willem Coward, Samuel Lupu, Andrei Foster, Thomas Rocktäschel, Tim Foerster, Jakob |
| contents | Recent advances in reasoning models have yielded impressive results in mathematics and coding. However, most approaches rely on static datasets, which have been suggested to encourage memorisation and limit generalisation. We introduce DéjàQ, a framework that departs from this paradigm by jointly evolving a diverse set of synthetic mathematical problems alongside model training. This evolutionary process adapts to the model's ability throughout training, optimising problems for learnability. We propose two LLM-driven mutation strategies in which the model itself mutates the training data, either by altering contextual details or by directly modifying problem structure. We find that the model can generate novel and meaningful problems, and that these LLM-driven mutations improve RL training. We analyse key aspects of DéjàQ, including the validity of generated problems and computational overhead. Our results underscore the potential of dynamically evolving training data to enhance mathematical reasoning and indicate broader applicability, which we will support by open-sourcing our code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01931 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems Röpke, Willem Coward, Samuel Lupu, Andrei Foster, Thomas Rocktäschel, Tim Foerster, Jakob Machine Learning Artificial Intelligence Recent advances in reasoning models have yielded impressive results in mathematics and coding. However, most approaches rely on static datasets, which have been suggested to encourage memorisation and limit generalisation. We introduce DéjàQ, a framework that departs from this paradigm by jointly evolving a diverse set of synthetic mathematical problems alongside model training. This evolutionary process adapts to the model's ability throughout training, optimising problems for learnability. We propose two LLM-driven mutation strategies in which the model itself mutates the training data, either by altering contextual details or by directly modifying problem structure. We find that the model can generate novel and meaningful problems, and that these LLM-driven mutations improve RL training. We analyse key aspects of DéjàQ, including the validity of generated problems and computational overhead. Our results underscore the potential of dynamically evolving training data to enhance mathematical reasoning and indicate broader applicability, which we will support by open-sourcing our code. |
| title | DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.01931 |