Metraipolis › archive › dc_c2a2ced7559b
SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning — arXiv:2608.17301
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.17301
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:28:35.780Z
- SHA-256 of the archived text
ec205e589d0907021ee281a22185748a38931b071f7c0b41d9acd7946919a230- Stable URL of this page
https://metraipolis.com/documento/dc_c2a2ced7559b
How to cite
SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning — arXiv:2608.17301 — arXiv (en), https://arxiv.org/abs/2608.17301 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2a2ced7559b (Metraipolis archive dc_c2a2ced7559b, sha256 ec205e589d0907021ee281a22185748a38931b071f7c0b41d9acd7946919a230)
BibTeX
@misc{dcc2a2ced7559b,
title = {SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning — arXiv:2608.17301},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.17301},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2a2ced7559b; sha256 ec205e589d0907021ee281a22185748a38931b071f7c0b41d9acd7946919a230},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17301. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Post-training with supervised chain-of-thought fine-tuning and reinforcement learning from verifiable rewards has substantially improved the mathematical reasoning capabilities of large language models (LLMs). However, their application to signal processing problems remains relatively under-explored. This report investigates reinforcement fine-tuning strategies for adapting Qwen2.5-3B-Base to graduate-level signal mathematical problems from WirelessMATHBench-XL, a comprehensive benchmark for mathematical reasoning in this domain. We examine two training paradigms: (i) direct reinforcement learning (RL) on WirelessMATHBench-XL with verifiable rewards; and (ii) supervised fine-tuning (SFT) on a distilled wireless-domain chain-of-thought corpus, followed by the same domain-specific RL stage. Across both paradigms, we benchmark Group Relative Policy Optimization (GRPO), Group Sequence Policy Optimization (GSPO), and Geometric-Mean Policy Optimization (GMPO). We aim to assess whether domain-aware CoT SFT serves as an effective initialization for subsequent RL, and whether GSPO or GMPO offer advantages in stability or accuracy over GRPO for signal reasoning tasks. Our best model achieves an overall accuracy of 39.12\%, representing a more than threefold improvement over the untrained Base model (12.37\%). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.17301 — 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 2026-10-18T14:27:54.252Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).