Metraipolis › archive › dc_eddb98eda44f

AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance — arXiv:2611.04079

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04079
License (as archived): CC0-1.0
Archived: 2026-11-04T21:37:43.853Z
SHA-256 of the archived text: f09fd5103914415896747fa8ade2c32ce2812d51e92a0e328442ce891560f3d1
Stable URL of this page: https://metraipolis.com/documento/dc_eddb98eda44f

How to cite

AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance — arXiv:2611.04079 — arXiv (en), https://arxiv.org/abs/2611.04079 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eddb98eda44f (Metraipolis archive dc_eddb98eda44f, sha256 f09fd5103914415896747fa8ade2c32ce2812d51e92a0e328442ce891560f3d1)

BibTeX

@misc{dceddb98eda44f,
  title = {AlgoPilot: Cross-Paradigm Reasoning in Language Models via Strategy Selection and Guidance — arXiv:2611.04079},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04079},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eddb98eda44f; sha256 f09fd5103914415896747fa8ade2c32ce2812d51e92a0e328442ce891560f3d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04079. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-world problems span diverse domains, including program synthesis, symbolic reasoning, planning, and optimization, and often require fundamentally different solution paradigms. A central challenge for LLM-based reasoning is twofold: identifying an appropriate problem-solving approach and formulating it correctly. In this paper, we propose AlgoPilot, a cross-paradigm reasoning framework that enables adaptive selection of the solving approaches and structured problem formulation prior to execution. The AlgoPilot framework contains three components: 1) a SteerLM, trained via supervised fine-tuning (SFT) and reinforcement learning (RL), that adaptively selects the solving strategy (paradigm and modes) based on input problems, 2) the corresponding expert GuideLM, trained via SFT, that generates structured formulation guidance tailored to the selected strategy, and 3) an ExecutionLM that generates solutions conditioned on both the selected strategy and its formulation. Unlike prompting-based methods that rely on fixed reasoning templates, our approach learns to adaptively choose and structure problem-solving strategies based on the input. We build AlgoPilot on Qwen3-8B and evaluate across 5 problem categories and 13 benchmarks with 66 unique domains, comparing against both the latest similarly scaled small models and large LLMs. AlgoPilot significantly improves average accuracy for the same model from 38.4% to 72.9%, outperforming the best large LLM prompting baseline GLM-5 by 11.7%. Ablation studies confirm the effectiveness of each component. Notably, we show that the learned steering and formulation modules can transfer across execution models, suggesting their potential to improve other LLMs. Project page: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04079 — 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 2026-11-04T21:35:49.513Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).