Metraipolis › archive › dc_8e09531f034b
Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models — arXiv:2610.12168
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.12168
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:50:38.059Z
- SHA-256 of the archived text
aed921fe4c64ac97edb4da923be8d4b91eefa85447c6bfb8273766b544645643- Stable URL of this page
https://metraipolis.com/documento/dc_8e09531f034b
How to cite
Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models — arXiv:2610.12168 — arXiv (en), https://arxiv.org/abs/2610.12168 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8e09531f034b (Metraipolis archive dc_8e09531f034b, sha256 aed921fe4c64ac97edb4da923be8d4b91eefa85447c6bfb8273766b544645643)
BibTeX
@misc{dc8e09531f034b,
title = {Learning to Plan by Looking Back: Hindsight Hierarchies for Training Reasoning Models — arXiv:2610.12168},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.12168},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8e09531f034b; sha256 aed921fe4c64ac97edb4da923be8d4b91eefa85447c6bfb8273766b544645643},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12168. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's current solving abilities, an additionally supplied solution might enable the model to extract useful solution ideas in hindsight. We operationalize this by jointly training the same model to exhibit the following three capabilities: predicting solution ideas from problems alone, reverse-engineering ideas from problems and known solutions, and solving problems using provided ideas. The loop alternates between reverse engineering such ideas from problems with supplied solutions and using these ideas as additional supervision for joint training of all three capabilities. We give a formal specification of our method and a concrete instantiation for interactive theorem proving in the Lean theorem prover; empirical evaluation remains future work. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Logic in Computer Science (cs.LO). Pagina del lavoro: https://arxiv.org/abs/2610.12168 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T05:47:01.089Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).