# SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoning

arXiv: https://arxiv.org/abs/2608.17301 · HTML: https://mlsanity.com/paper/2608.17301/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset](https://mlsanity.com/paper/2402.10176/) (2024)
- [Geometric-Mean Policy Optimization](https://mlsanity.com/paper/2507.20673/) (2025)
- [Large Language Models for Telecom: Forthcoming Impact on the Industry](https://mlsanity.com/paper/2308.06013/) (2023)
- [TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models](https://mlsanity.com/paper/2407.09424/) (2024)
- [Wireless Communications Through Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/1906.09490/) (2019)
- [Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications](https://mlsanity.com/paper/2409.05314/) (2024)
- [A Survey on Fundamental Limits of Integrated Sensing and Communication](https://mlsanity.com/paper/2104.09954/) (2021)
- [WirelessBench: A Tolerance-Aware LLM Agent Benchmark for Wireless Network Intelligence](https://mlsanity.com/paper/2603.21251/) (2026)
- [TeleMath: A Benchmark for Large Language Models in Telecom Mathematical Problem Solving](https://mlsanity.com/paper/2506.10674/) (2025)
- [WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications](https://mlsanity.com/paper/2505.14354/) (2025)
- [WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning](https://mlsanity.com/paper/2509.23219/) (2025)
- [RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following](https://mlsanity.com/paper/2605.25851/) (2026)

## Abstract (arXiv)

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%).