Metraipolis › archive › dc_fda96c2a86af
Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge — arXiv:2609.34327
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34327
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:57:40.393Z
- SHA-256 of the archived text
ef70ff0a72d6367876fbf7438ebd5580fedae5f21590594ab52740f3edd5e447- Stable URL of this page
https://metraipolis.com/documento/dc_fda96c2a86af
How to cite
Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge — arXiv:2609.34327 — arXiv (en), https://arxiv.org/abs/2609.34327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fda96c2a86af (Metraipolis archive dc_fda96c2a86af, sha256 ef70ff0a72d6367876fbf7438ebd5580fedae5f21590594ab52740f3edd5e447)
BibTeX
@misc{dcfda96c2a86af,
title = {Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge — arXiv:2609.34327},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34327},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fda96c2a86af; sha256 ef70ff0a72d6367876fbf7438ebd5580fedae5f21590594ab52740f3edd5e447},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scaling test-time computation is a powerful way to improve language-model reasoning, and is particularly appealing for small reasoning models (sRMs) that are cheap to serve. However, is additional thinking always the right operation? By intervening at intermediate reasoning states across two model families and multiple scales, we find that self-refinement largely consolidates probability mass onto solutions already reachable from the current state, rather than making new ones reachable. These interventions reveal two failure regimes: execution bottlenecks, where the correct path is reachable and reflection can recover it, and knowledge bottlenecks, where relevant external information makes it reachable. Motivated by this distinction, we introduce FlyBy, a selective querying framework, and train 4B and 8B variants to reason first, diagnose what remains unresolved, and, at a knowledge bottleneck, query stronger models whose parametric knowledge extends beyond its own. Supervised fine-tuning bootstraps a multi-depth query action, and cost-aware reinforcement learning calibrates whether to query, what to ask, and how much to spend. On 1,158 hard problems across six benchmarks, FlyBy-4B achieves 45.96% pass@8, surpassing Qwen3-14B (41.64%) at 2.7 times lower serving cost, while also exceeding Qwen3-8B in pass@1 (16.85% vs. 15.31%). Scaling to FlyBy-8B further improves pass@8 to 51.81%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.34327 — 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 2026-10-07T20:29:01.516Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).