{"ID":2864465,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24085","arxiv_id":"2509.24085","title":"PEARL: Peer-Enhanced Adaptive Radio via On-Device LLM","abstract":"We present PEARL (Peer-Enhanced Adaptive Radio via On-Device LLM), a framework for cooperative cross-layer optimization in device-to-device (D2D) communication. Building on our previous work on single-device on-device LLMs, PEARL extends the paradigm by leveraging both publisher and subscriber states to guide Wi-Fi Aware (WA) parameter selection. A context-aware reward, which normalizes latency by application tolerances and modulates energy by device battery states, provides richer supervision for KL-based finetuning. We study two lightweight variants: PEARL (Head + Low-Rank Adaptation (LoRA)) achieves the best overall performance, while PEARL-Lite (Head-only) delivers sub-20 ms inference at near-identical objective scores. Across synthetic scenarios grounded in real measurements, PEARL improves objective scores over heuristic and compact model baselines and reduces energy by up to 16% in cooperative low-battery cases. These results demonstrate that peer-aware context, reward-aligned training, and head-based efficiency make LLMs practical for always-on, on-device cross-layer control. Code, real-world demo, and dataset are available at https://github.com/abman23/pearl","short_abstract":"We present PEARL (Peer-Enhanced Adaptive Radio via On-Device LLM), a framework for cooperative cross-layer optimization in device-to-device (D2D) communication. Building on our previous work on single-device on-device LLMs, PEARL extends the paradigm by leveraging both publisher and subscriber states to guide Wi-Fi Awa...","url_abs":"https://arxiv.org/abs/2509.24085","url_pdf":"https://arxiv.org/pdf/2509.24085v2","authors":"[\"Ju-Hyung Lee\",\"Yanqing Lu\",\"Klaus Doppler\"]","published":"2025-09-28T21:43:17Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.NI\",\"eess.SP\"]","methods":"[\"Large Language Model\",\"LoRA\"]","has_code":false,"code_links":[{"ID":609154,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2864465,"paper_url":"https://arxiv.org/abs/2509.24085","paper_title":"PEARL: Peer-Enhanced Adaptive Radio via On-Device LLM","repo_url":"https://github.com/abman23/pearl","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}