The paper introduces CRAFT, a data‑centric fine‑tuning approach that aligns small language models (SLMs) for pre‑hoc reasoning in AI‑native 6G radio access networks (RAN). By automatically generating verified (input, trace, label) triplets and fine‑tuning with low‑rank adaptation, CRAFT achieves high accuracy and F1 scores on TRACTOR and IC xApp datasets while avoiding parse failures that plague RL methods like GRPO. It also reduces energy consumption by 59% compared to GRPO baselines, offering a more sustainable path to auditable AI in 6G RAN.
By Pranshav Gajjar, Vijay K Shah
TelecomGPT‑R1‑9B is an open‑source large language model designed specifically for telecom reasoning tasks. It was trained on a 67,427‑example supervised fine‑tuning corpus that covers protocol, knowledge, modeling, and fault reasoning, and further refined with a two‑stage post‑training process involving low‑rank adaptation and policy optimization. The model tops the GSMA open telco leaderboard and matches state‑of‑the‑art closed‑source reasoners across seven public telecom benchmarks.
By Bohao Wang, Chenwei Wu, Haoyu Li, Hang Zou, Yu Tian, Lina Bariah, Li Wei, Chongwen Huang, Yongliang Shen, Zhaoyang Zhang, Merouane Debbah
TelecomGPT‑R1 is an open‑source family of unified telecom reasoning models that address the limitations of existing telecom‑specific and general‑purpose LLMs. It is built on a four‑axis framework—protocol, knowledge, modeling, and fault—and trained on a curated corpus of 104,880 verified question‑answer pairs with chain‑of‑thought reasoning. After supervised fine‑tuning, dynamic sampling policy optimization with task‑routed rubric rewards is used to stabilize reinforcement learning across heterogeneous telecom tasks, achieving an 89.64% mean score on seven GSMA Open Telco Leaderboard benchmarks, surpassing leading proprietary models.
By Bohao Wang, Chenwei Wu, Hang Zou, Yu Tian, Lina Bariah, Li Wei, Chongwen Huang, Yongliang Shen, Zhaoyang Zhang, Merouane Debbah
TRACES (Tagging Reasoning Steps for Adaptive Cost‑Efficient Early‑Stopping) is a lightweight framework that tags reasoning steps of large‑language models in real time, enabling adaptive, cost‑efficient early stopping during inference. By monitoring the types of steps generated, the method identifies when models shift their reasoning after arriving at a correct answer, allowing for interpretable stopping criteria. Experiments on mathematical reasoning benchmarks (MATH500, GSM8K, AIME) and knowledge benchmarks (MMLU, GPQA) show token reductions of 20–50% while preserving accuracy, with more conservative thresholds needed for harder tasks such as BeyondAIME and IMO AnswerBench.
By Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo, John D. Kelleher
arXiv:2607. 20448v1 Announce Type: cross Abstract: We introduce Domyn-Small, a 10-billion-parameter open-weight reasoning language model released under the MIT license.
By Simone Angarano, Francesco Bertolotti, Federico D'Ambrosio, Michele Resta, Alessandro Rognoni, Nicol\`o Ruggeri, Dario Salvati, Andrea Valenti, Alberto Veneri, Martin Cimmino
arXiv:2606. 26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization.
By Qiaobo Hao, Yangqian Wu, Shunyi Wang, Zhongjian Zhang, Ziqun Li, Yayin He, Muqing Li, Chen Zhong
arXiv:2510. 27544v3 Announce Type: replace Abstract: Current training paradigms, optimized for long-horizon reasoning trace execution, have made Large Language Models (LLMs) excel at pattern matching and forward simulation of reasoning, but underperform at counterfactual causal understanding and reasoning.
By Nikolaus Holzer, William Fishell, Baishakhi Ray, Mark Santolucito
SWE-Critix is a post‑training pipeline that creates generalist verifiers for coding‑agent trajectories. It uses supervised fine‑tuning followed by reinforcement learning to train 30B models on CodeForge‑Preview data, enabling the verifier to predict completion labels and generate natural‑language explanations. The approach raises classification accuracy from 57% to 78% on a held‑out test set.
By Jiajun Hu, Chun Yong Chong
arXiv:2509. 16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks.
By Jiahao Yu, Zelei Cheng, Xian Wu, Xinyu Xing
arXiv:2606. 05402v1 Announce Type: cross Abstract: Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the reasoning process.
By Jinu Lee, Shivam Agarwal, Amruta Parulekar, Siddarth Madala, Dilek Hakkani-Tur, Julia Hockenmaier
Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization.
arXiv:2511. 08577v3 Announce Type: replace-cross Abstract: Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications.
By Tianyu Fu, Yichen You, Zekai Chen, Guohao Dai, Huazhong Yang, Yu Wang