mlsanityData to 7 Oct 2026

WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning

arXiv 2509.23219 ↗First posted 27 Sep 2025cs.LGcited by 3

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

Technical-domain benchmarks constructed from arXiv papers can overlap the same public text used in LLM pretraining. Auditing this risk at training-corpus scale requires searching billions of corpus n-grams while retaining per-item evidence that users can inspect and recompute. We contribute a reverse-probe audit at a fixed 13-gram threshold: it indexes benchmark prompts, streams public pretraining corpora, and emits per-problem prompt-surface lexical-overlap metadata with memory that scales with the benchmark. We instantiate the protocol in WirelessMathBench-XL, a 4,027-problem wireless mathematical-reasoning benchmark built from 836 retained arXiv papers across 20 subfields. Against 12.9B streamed 13-grams from RedPajama-arXiv, the audit identifies a strict zero-hit view S0 covering 3,853 problems (95.7%). Filtering to S0 changes accuracy by less than 1 pp for every evaluated model; frontier calibration rows form one high-accuracy cluster between 86.5% and 91.3%, not a resolved rank order. Only 30/800 test items carry detected overlap. Under an all-flagged-correct counterfactual, their largest possible positive score inflation is 0.31-0.51 pp for the frontier rows, so full-versus-S0 is a bounded, structurally underpowered stability summary rather than a contamination-effect test or cleanliness claim. The audit channel does not cover paraphrase, target-answer, post-training, or closed-corpus exposure. The release includes source-paper identifiers, verifier-facing ground truths, audit and threshold metadata, filtered views, a paper-disjoint sensitivity view, evaluation traces, paired-bootstrap scripts, training recipes, Croissant metadata, and a Datasheet for Datasets.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 33 references that are in the map. First posted on arXiv 27 Sep 2025.

Builds on

27 of 33 references.

References · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2018Datasheets for Datasetscited by 1,371
  7. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  8. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
  9. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  10. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 533
  11. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 475
  12. 2023Llemma: An Open Language Model For Mathematicscited by 385
15 more
  1. 2023Detecting Pretraining Data from Large Language Modelscited by 375
  2. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 339
  3. 2023Proving Test Set Contamination in Black Box Language Modelscited by 227
  4. 2023Time Travel in LLMs: Tracing Data Contamination in Large Language Modelscited by 175
  5. 2023OpenWebMath: An Open Dataset of High-Quality Mathematical Web Textcited by 151
  6. 2024Benchmark Data Contamination of Large Language Models: A Surveycited by 138
  7. 2023Investigating Data Contamination in Modern Benchmarks for Large Language Modelscited by 136
  8. 2023What's In My Big Data?cited by 129
  9. 2024Croissant: A Metadata Format for ML-Ready Datasetscited by 79
  10. 2025Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Modelscited by 65
  11. 2023TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledgecited by 62
  12. 2024MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Datacited by 51
  13. 2024WirelessLLM: Empowering Large Language Models Towards Wireless Intelligencecited by 43
  14. 2024Tele-LLMs: A Series of Specialized Large Language Models for Telecommunicationscited by 25
  15. 2025WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communicationscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026SignalReasoner: Assessing the Upper Bound of 3B Models for Signal Mathematical Reasoningcited by 0
  2. 2026TelecomGPT-R1: A Unified Open-Source Reasoner for the Telecom Stackcited by 0
  3. 2026TelecomGPT-R1: Unified Post-Training for Reasoning Across Heterogeneous Telecom Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Large Language Model (LLM)-enabled Reinforcement Learning for Wireless Network Optimization
  2. 2025LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning
  3. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
  4. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
  5. 2025Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning
  6. 2025MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
  7. 2025No Free Lunch: Rethinking Internal Feedback for LLM Reasoning
  8. 2025Bridging Offline and Online Reinforcement Learning for LLMs