Metraipolis › archive › dc_4f2b95ac99c2
Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries — arXiv:2610.06269
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06269
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:25:30.397Z
- SHA-256 of the archived text
8a712297fa3e3b9ffa4468d49c67dc3df6acaae321bebcdd2d326bf037a8c66b- Stable URL of this page
https://metraipolis.com/documento/dc_4f2b95ac99c2
How to cite
Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries — arXiv:2610.06269 — arXiv, https://arxiv.org/abs/2610.06269 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f2b95ac99c2 (Metraipolis archive dc_4f2b95ac99c2, sha256 8a712297fa3e3b9ffa4468d49c67dc3df6acaae321bebcdd2d326bf037a8c66b)
BibTeX
@misc{dc4f2b95ac99c2,
title = {Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries — arXiv:2610.06269},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06269},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f2b95ac99c2; sha256 8a712297fa3e3b9ffa4468d49c67dc3df6acaae321bebcdd2d326bf037a8c66b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06269. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Open-ended scientific discovery often requires repeatedly proposing and evaluating candidate solutions. LLM-based systems can support this process by generating and refining executable solutions from verifier feedback. Methods such as TTT-Discover use test-time training (TTT) to update the solution-generating LLM from verifier feedback, adapting its generation policy to improve subsequent proposals on the target problem. However, this becomes expensive when reliable execution requires a large model, since training must maintain gradients, optimizer states, and policy statistics while repeatedly generating long, structured outputs. It also complicates credit assignment: outcome-level verifier feedback must jointly evaluate the high-level strategy and its low-level implementation. In this work, we introduce Guidance-TTT, which separates these roles. A compact guidance model is trained at test time to propose high-level strategic changes, while a frozen execution model implements them as complete executable solutions. At each step, the system selects a promising previously discovered solution, proposes a change, executes and verifies it, and updates only the guidance model using an adaptive group-relative RL objective. This concentrates test-time learning on short strategic decisions while retaining the implementation capability of a substantially stronger model without adapting it. Without web access, Guidance-TTT produces strong solutions across four distinct domains: combinatorial optimization (Polyomino Packing), heuristic programming (AHC058), machine learning (Lasso), and GPU kernel optimization (TriMul). Across these tasks, it outperforms the best solutions reported in prior work while remaining competitive with state-of-the-art results on public online leaderboards. Code is available at this https URL . 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). Pagina del lavoro: https://arxiv.org/abs/2610.06269 — 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 2026-10-06T05:24:05.665Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).